diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/README.md b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/README.md
similarity index 97%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/README.md
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/README.md
index 68498bf3..ec365acb 100644
--- a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/README.md
+++ b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/README.md
@@ -1,4 +1,4 @@
-# codestral:22b-v0.1-fp16-0121
+# codestral:22b-v0.1-fp16-1802
 
 [![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
 [![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/apis/openapi.yaml b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/apis/openapi.yaml
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/apis/openapi.yaml
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/apis/schema.json b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/apis/schema.json
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/apis/schema.json
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/apis/schema.json
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/bento.yaml b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/bento.yaml
similarity index 93%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/bento.yaml
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/bento.yaml
index a4009c37..a0f94fcf 100644
--- a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/bento.yaml
+++ b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: codestral
-version: 22b-v0.1-fp16-0121
+version: 22b-v0.1-fp16-1802
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:46:07.037518+00:00'
+creation_time: '2024-09-27T22:06:09.973226+00:00'
 labels:
   model_name: mistralai/Codestral-22B-v0.1
   openllm_alias: 22b,22b-v0.1
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-a100-80g
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: codestral
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/docker/Dockerfile b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/docker/Dockerfile
similarity index 98%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/docker/Dockerfile
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/docker/Dockerfile
index 6a314dec..68790ac6 100644
--- a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/docker/Dockerfile
+++ b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/docker/Dockerfile
@@ -34,6 +34,8 @@ ARG BENTO_USER=bentoml
 ARG BENTO_USER_UID=1034
 ARG BENTO_USER_GID=1034
 RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
 ARG BENTO_PATH=/home/bentoml/bento
 ENV BENTO_PATH=$BENTO_PATH
 ENV BENTOML_HOME=/home/bentoml/
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/docker/entrypoint.sh b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/docker/entrypoint.sh
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/python/install.sh b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/python/install.sh
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/python/install.sh
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/python/requirements.lock.txt b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/python/requirements.lock.txt
similarity index 98%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/python/requirements.lock.txt
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/python/requirements.lock.txt
index cf2d88c8..ed9d9aa3 100644
--- a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/python/requirements.lock.txt
+++ b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/python/requirements.lock.txt
@@ -75,7 +75,7 @@ nvidia-ml-py==11.525.150
 nvidia-nccl-cu12==2.20.5
 nvidia-nvjitlink-cu12==12.6.68
 nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
+openai==1.50.1
 opentelemetry-api==1.20.0
 opentelemetry-instrumentation==0.41b0
 opentelemetry-instrumentation-aiohttp-client==0.41b0
@@ -139,8 +139,8 @@ triton==3.0.0
 typing-extensions==4.12.2
 tzdata==2024.2
 urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
+uv==0.4.17
+uvicorn==0.31.0
 uvloop==0.20.0
 vllm==0.6.2
 watchfiles==0.24.0
@@ -150,5 +150,5 @@ wrapt==1.16.0
 wsproto==1.2.0
 xformers==0.0.27.post2
 xxhash==3.5.0
-yarl==1.13.0
+yarl==1.13.1
 zipp==3.20.2
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/python/requirements.txt b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/python/requirements.txt
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/python/requirements.txt
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/python/version.txt b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/python/version.txt
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/env/python/version.txt
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/bentofile.yaml b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/bentofile.yaml
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/bentofile.yaml
index a50e2d7f..9a500740 100644
--- a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/bentofile.yaml
+++ b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/openllm_config.yaml b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/openllm_config.yaml
similarity index 92%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/openllm_config.yaml
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/openllm_config.yaml
index 16d31bec..200faba5 100644
--- a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/openllm_config.yaml
+++ b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/openllm_config.yaml
@@ -4,6 +4,8 @@ engine_config:
   enforce_eager: true
   max_model_len: 8192
   model: mistralai/Codestral-22B-v0.1
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: mistralai/Codestral-22B-v0.1
   openllm_alias: 22b,22b-v0.1
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/service.py b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/service.py
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/service.py
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/service.py
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/404.html b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/404.html
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/404.html
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/apple-touch-icon.png b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/apple-touch-icon.png
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/chat.html b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/chat.html
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/chat.html
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/chat.txt b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/chat.txt
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/chat.txt
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/favicon-16x16.png b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/favicon-16x16.png
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/favicon.ico b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/favicon.ico
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/favicon.ico
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/index.html b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/index.html
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/index.html
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/index.txt b/bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/src/ui/index.txt
rename to bentoml/bentos/codestral/22b-v0.1-fp16-1802/src/ui/index.txt
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/README.md b/bentoml/bentos/gemma/2b-instruct-fp16-f738/README.md
similarity index 97%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/README.md
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/README.md
index a89534b2..58a7d7e6 100644
--- a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/README.md
+++ b/bentoml/bentos/gemma/2b-instruct-fp16-f738/README.md
@@ -1,4 +1,4 @@
-# gemma:2b-instruct-fp16-9aec
+# gemma:2b-instruct-fp16-f738
 
 [![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
 [![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/apis/openapi.yaml b/bentoml/bentos/gemma/2b-instruct-fp16-f738/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/apis/openapi.yaml
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/apis/openapi.yaml
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/apis/schema.json b/bentoml/bentos/gemma/2b-instruct-fp16-f738/apis/schema.json
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/apis/schema.json
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/apis/schema.json
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/bento.yaml b/bentoml/bentos/gemma/2b-instruct-fp16-f738/bento.yaml
similarity index 92%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/bento.yaml
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/bento.yaml
index ff927053..1a659404 100644
--- a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/bento.yaml
+++ b/bentoml/bentos/gemma/2b-instruct-fp16-f738/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: gemma
-version: 2b-instruct-fp16-9aec
+version: 2b-instruct-fp16-f738
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:48:00.129302+00:00'
+creation_time: '2024-09-27T22:07:16.146695+00:00'
 labels:
   model_name: google/gemma-2b-it
   openllm_alias: 2b,2b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-rtx-3060
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: gemma
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/env/docker/Dockerfile b/bentoml/bentos/gemma/2b-instruct-fp16-f738/env/docker/Dockerfile
similarity index 98%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/env/docker/Dockerfile
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/env/docker/Dockerfile
index 6a314dec..68790ac6 100644
--- a/bentoml/bentos/llama2/13b-chat-fp16-eb70/env/docker/Dockerfile
+++ b/bentoml/bentos/gemma/2b-instruct-fp16-f738/env/docker/Dockerfile
@@ -34,6 +34,8 @@ ARG BENTO_USER=bentoml
 ARG BENTO_USER_UID=1034
 ARG BENTO_USER_GID=1034
 RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
 ARG BENTO_PATH=/home/bentoml/bento
 ENV BENTO_PATH=$BENTO_PATH
 ENV BENTOML_HOME=/home/bentoml/
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/docker/entrypoint.sh b/bentoml/bentos/gemma/2b-instruct-fp16-f738/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/docker/entrypoint.sh
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/python/install.sh b/bentoml/bentos/gemma/2b-instruct-fp16-f738/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/python/install.sh
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/env/python/install.sh
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/python/requirements.lock.txt b/bentoml/bentos/gemma/2b-instruct-fp16-f738/env/python/requirements.lock.txt
similarity index 98%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/python/requirements.lock.txt
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/env/python/requirements.lock.txt
index cf2d88c8..ed9d9aa3 100644
--- a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/python/requirements.lock.txt
+++ b/bentoml/bentos/gemma/2b-instruct-fp16-f738/env/python/requirements.lock.txt
@@ -75,7 +75,7 @@ nvidia-ml-py==11.525.150
 nvidia-nccl-cu12==2.20.5
 nvidia-nvjitlink-cu12==12.6.68
 nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
+openai==1.50.1
 opentelemetry-api==1.20.0
 opentelemetry-instrumentation==0.41b0
 opentelemetry-instrumentation-aiohttp-client==0.41b0
@@ -139,8 +139,8 @@ triton==3.0.0
 typing-extensions==4.12.2
 tzdata==2024.2
 urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
+uv==0.4.17
+uvicorn==0.31.0
 uvloop==0.20.0
 vllm==0.6.2
 watchfiles==0.24.0
@@ -150,5 +150,5 @@ wrapt==1.16.0
 wsproto==1.2.0
 xformers==0.0.27.post2
 xxhash==3.5.0
-yarl==1.13.0
+yarl==1.13.1
 zipp==3.20.2
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/python/requirements.txt b/bentoml/bentos/gemma/2b-instruct-fp16-f738/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/python/requirements.txt
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/env/python/requirements.txt
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/python/version.txt b/bentoml/bentos/gemma/2b-instruct-fp16-f738/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/python/version.txt
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/env/python/version.txt
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/bentofile.yaml b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/bentofile.yaml
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/bentofile.yaml
index 84b71fd7..15bec738 100644
--- a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/bentofile.yaml
+++ b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/openllm_config.yaml b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/openllm_config.yaml
similarity index 90%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/openllm_config.yaml
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/openllm_config.yaml
index 8016c3c2..e107d582 100644
--- a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/openllm_config.yaml
+++ b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/openllm_config.yaml
@@ -2,6 +2,8 @@ engine_config:
   dtype: half
   max_model_len: 2048
   model: google/gemma-2b-it
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: google/gemma-2b-it
   openllm_alias: 2b,2b-instruct
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/service.py b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/service.py
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/service.py
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/service.py
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/404.html b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/404.html
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/404.html
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/apple-touch-icon.png b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/apple-touch-icon.png
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/chat.html b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/chat.html
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/chat.html
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/chat.txt b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/chat.txt
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/chat.txt
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/favicon-16x16.png b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/favicon-16x16.png
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/favicon.ico b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/favicon.ico
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/favicon.ico
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/index.html b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/index.html
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/index.html
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/index.txt b/bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/src/ui/index.txt
rename to bentoml/bentos/gemma/2b-instruct-fp16-f738/src/ui/index.txt
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/README.md b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/README.md
similarity index 97%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/README.md
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/README.md
index 8c8d1b85..dff86cb0 100644
--- a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/README.md
+++ b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/README.md
@@ -1,4 +1,4 @@
-# gemma:7b-instruct-fp16-5dec
+# gemma:7b-instruct-fp16-7ca0
 
 [![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
 [![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/apis/openapi.yaml b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/apis/openapi.yaml
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/apis/openapi.yaml
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/apis/schema.json b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/apis/schema.json
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/apis/schema.json
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/apis/schema.json
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/bento.yaml b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/bento.yaml
similarity index 92%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/bento.yaml
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/bento.yaml
index fe659de1..acbb0f12 100644
--- a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/bento.yaml
+++ b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: gemma
-version: 7b-instruct-fp16-5dec
+version: 7b-instruct-fp16-7ca0
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:48:05.798990+00:00'
+creation_time: '2024-09-27T22:07:21.267621+00:00'
 labels:
   model_name: google/gemma-7b-it
   openllm_alias: 7b,7b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-tesla-l4
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: gemma
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/docker/Dockerfile b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/docker/Dockerfile
similarity index 98%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/docker/Dockerfile
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/docker/Dockerfile
index 6a314dec..68790ac6 100644
--- a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/docker/Dockerfile
+++ b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/docker/Dockerfile
@@ -34,6 +34,8 @@ ARG BENTO_USER=bentoml
 ARG BENTO_USER_UID=1034
 ARG BENTO_USER_GID=1034
 RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
 ARG BENTO_PATH=/home/bentoml/bento
 ENV BENTO_PATH=$BENTO_PATH
 ENV BENTOML_HOME=/home/bentoml/
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/docker/entrypoint.sh b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/docker/entrypoint.sh
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/python/install.sh b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/python/install.sh
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/python/install.sh
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/env/python/requirements.lock.txt b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/python/requirements.lock.txt
similarity index 98%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/env/python/requirements.lock.txt
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/python/requirements.lock.txt
index cf2d88c8..ed9d9aa3 100644
--- a/bentoml/bentos/llama2/13b-chat-fp16-eb70/env/python/requirements.lock.txt
+++ b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/python/requirements.lock.txt
@@ -75,7 +75,7 @@ nvidia-ml-py==11.525.150
 nvidia-nccl-cu12==2.20.5
 nvidia-nvjitlink-cu12==12.6.68
 nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
+openai==1.50.1
 opentelemetry-api==1.20.0
 opentelemetry-instrumentation==0.41b0
 opentelemetry-instrumentation-aiohttp-client==0.41b0
@@ -139,8 +139,8 @@ triton==3.0.0
 typing-extensions==4.12.2
 tzdata==2024.2
 urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
+uv==0.4.17
+uvicorn==0.31.0
 uvloop==0.20.0
 vllm==0.6.2
 watchfiles==0.24.0
@@ -150,5 +150,5 @@ wrapt==1.16.0
 wsproto==1.2.0
 xformers==0.0.27.post2
 xxhash==3.5.0
-yarl==1.13.0
+yarl==1.13.1
 zipp==3.20.2
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/python/requirements.txt b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/python/requirements.txt
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/python/requirements.txt
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/python/version.txt b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/env/python/version.txt
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/env/python/version.txt
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/bentofile.yaml b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/bentofile.yaml
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/bentofile.yaml
index 944444c0..9226e155 100644
--- a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/bentofile.yaml
+++ b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/openllm_config.yaml b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/openllm_config.yaml
similarity index 90%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/openllm_config.yaml
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/openllm_config.yaml
index 83ac4b15..f44d687c 100644
--- a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/openllm_config.yaml
+++ b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/openllm_config.yaml
@@ -2,6 +2,8 @@ engine_config:
   dtype: half
   max_model_len: 2048
   model: google/gemma-7b-it
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: google/gemma-7b-it
   openllm_alias: 7b,7b-instruct
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/service.py b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/service.py
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/service.py
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/service.py
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/404.html b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/404.html
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/404.html
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/apple-touch-icon.png b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/apple-touch-icon.png
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/chat.html b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/chat.html
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/chat.html
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/chat.txt b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/chat.txt
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/chat.txt
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/favicon-16x16.png b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/favicon-16x16.png
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/favicon.ico b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/favicon.ico
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/favicon.ico
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/index.html b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/index.html
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/index.html
diff --git a/bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/index.txt b/bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/gemma/7b-instruct-fp16-5dec/src/ui/index.txt
rename to bentoml/bentos/gemma/7b-instruct-fp16-7ca0/src/ui/index.txt
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/README.md b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/README.md
similarity index 97%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/README.md
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/README.md
index a4362420..eba957c2 100644
--- a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/README.md
+++ b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/README.md
@@ -1,4 +1,4 @@
-# gemma2:27b-instruct-fp16-c398
+# gemma2:27b-instruct-fp16-8ee8
 
 [![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
 [![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/apis/openapi.yaml b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/apis/openapi.yaml
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/apis/openapi.yaml
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/apis/schema.json b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/apis/schema.json
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/apis/schema.json
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/apis/schema.json
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/bento.yaml b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/bento.yaml
similarity index 93%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/bento.yaml
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/bento.yaml
index 52ab3569..e96d921b 100644
--- a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/bento.yaml
+++ b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: gemma2
-version: 27b-instruct-fp16-c398
+version: 27b-instruct-fp16-8ee8
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:47:54.539732+00:00'
+creation_time: '2024-09-27T22:07:11.043161+00:00'
 labels:
   model_name: google/gemma-2-27b-it
   openllm_alias: 27b,27b-instruct
@@ -26,6 +26,8 @@ services:
 envs:
 - name: VLLM_ATTENTION_BACKEND
   value: FLASHINFER
+- name: HF_TOKEN
+  value: ''
 schema:
   name: gemma2
   type: service
@@ -76,6 +78,7 @@ docker:
   cuda_version: null
   env:
     VLLM_ATTENTION_BACKEND: FLASHINFER
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/docker/Dockerfile b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/docker/Dockerfile
similarity index 98%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/docker/Dockerfile
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/docker/Dockerfile
index 7097bb4b..9f04e263 100644
--- a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/docker/Dockerfile
+++ b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/docker/Dockerfile
@@ -36,6 +36,8 @@ ARG BENTO_USER_GID=1034
 RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
 ARG VLLM_ATTENTION_BACKEND=FLASHINFER
 ENV VLLM_ATTENTION_BACKEND=$VLLM_ATTENTION_BACKEND
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
 ARG BENTO_PATH=/home/bentoml/bento
 ENV BENTO_PATH=$BENTO_PATH
 ENV BENTOML_HOME=/home/bentoml/
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/docker/entrypoint.sh b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/docker/entrypoint.sh
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/python/install.sh b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/python/install.sh
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/python/install.sh
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/python/requirements.lock.txt b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/python/requirements.lock.txt
similarity index 98%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/python/requirements.lock.txt
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/python/requirements.lock.txt
index e0a4d787..3e6b1e22 100644
--- a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/python/requirements.lock.txt
+++ b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/python/requirements.lock.txt
@@ -77,7 +77,7 @@ nvidia-ml-py==11.525.150
 nvidia-nccl-cu12==2.20.5
 nvidia-nvjitlink-cu12==12.6.68
 nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
+openai==1.50.1
 opentelemetry-api==1.20.0
 opentelemetry-instrumentation==0.41b0
 opentelemetry-instrumentation-aiohttp-client==0.41b0
@@ -141,8 +141,8 @@ triton==3.0.0
 typing-extensions==4.12.2
 tzdata==2024.2
 urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
+uv==0.4.17
+uvicorn==0.31.0
 uvloop==0.20.0
 vllm==0.6.2
 watchfiles==0.24.0
@@ -152,5 +152,5 @@ wrapt==1.16.0
 wsproto==1.2.0
 xformers==0.0.27.post2
 xxhash==3.5.0
-yarl==1.13.0
+yarl==1.13.1
 zipp==3.20.2
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/python/requirements.txt b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/python/requirements.txt
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/python/requirements.txt
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/python/version.txt b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/python/version.txt
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/env/python/version.txt
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/bentofile.yaml b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/bentofile.yaml
similarity index 96%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/bentofile.yaml
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/bentofile.yaml
index 662da50f..77d3282e 100644
--- a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/bentofile.yaml
+++ b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/bentofile.yaml
@@ -1,6 +1,7 @@
 envs:
 - name: VLLM_ATTENTION_BACKEND
   value: FLASHINFER
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/openllm_config.yaml b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/openllm_config.yaml
similarity index 96%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/openllm_config.yaml
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/openllm_config.yaml
index cbe350fa..5abdbce5 100644
--- a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/openllm_config.yaml
+++ b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/openllm_config.yaml
@@ -5,6 +5,7 @@ engine_config:
 extra_envs:
 - name: VLLM_ATTENTION_BACKEND
   value: FLASHINFER
+- name: HF_TOKEN
 extra_labels:
   model_name: google/gemma-2-27b-it
   openllm_alias: 27b,27b-instruct
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/service.py b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/service.py
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/service.py
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/service.py
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/404.html b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/404.html
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/404.html
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/apple-touch-icon.png b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/apple-touch-icon.png
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/chat.html b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/chat.html
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/chat.html
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/chat.txt b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/chat.txt
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/chat.txt
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/favicon-16x16.png b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/favicon-16x16.png
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/favicon.ico b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/favicon.ico
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/favicon.ico
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/index.html b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/index.html
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/index.html
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/index.txt b/bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/src/ui/index.txt
rename to bentoml/bentos/gemma2/27b-instruct-fp16-8ee8/src/ui/index.txt
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/README.md b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/README.md
similarity index 97%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/README.md
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/README.md
index 1aa9151c..5025944f 100644
--- a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/README.md
+++ b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/README.md
@@ -1,4 +1,4 @@
-# gemma2:9b-instruct-fp16-3101
+# gemma2:9b-instruct-fp16-e0c2
 
 [![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
 [![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/apis/openapi.yaml b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/apis/openapi.yaml
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/apis/openapi.yaml
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/apis/schema.json b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/apis/schema.json
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/apis/schema.json
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/apis/schema.json
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/bento.yaml b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/bento.yaml
similarity index 93%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/bento.yaml
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/bento.yaml
index 2d8f75da..f435fc9e 100644
--- a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/bento.yaml
+++ b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: gemma2
-version: 9b-instruct-fp16-3101
+version: 9b-instruct-fp16-e0c2
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:47:48.405034+00:00'
+creation_time: '2024-09-27T22:07:05.720352+00:00'
 labels:
   model_name: google/gemma-2-9b-it
   openllm_alias: 9b,9b-instruct
@@ -26,6 +26,8 @@ services:
 envs:
 - name: VLLM_ATTENTION_BACKEND
   value: FLASHINFER
+- name: HF_TOKEN
+  value: ''
 schema:
   name: gemma2
   type: service
@@ -76,6 +78,7 @@ docker:
   cuda_version: null
   env:
     VLLM_ATTENTION_BACKEND: FLASHINFER
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/docker/Dockerfile b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/docker/Dockerfile
similarity index 98%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/docker/Dockerfile
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/docker/Dockerfile
index 7097bb4b..9f04e263 100644
--- a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/docker/Dockerfile
+++ b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/docker/Dockerfile
@@ -36,6 +36,8 @@ ARG BENTO_USER_GID=1034
 RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
 ARG VLLM_ATTENTION_BACKEND=FLASHINFER
 ENV VLLM_ATTENTION_BACKEND=$VLLM_ATTENTION_BACKEND
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
 ARG BENTO_PATH=/home/bentoml/bento
 ENV BENTO_PATH=$BENTO_PATH
 ENV BENTOML_HOME=/home/bentoml/
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/docker/entrypoint.sh b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/docker/entrypoint.sh
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/python/install.sh b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/python/install.sh
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/python/install.sh
diff --git a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/python/requirements.lock.txt b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/python/requirements.lock.txt
similarity index 98%
rename from bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/python/requirements.lock.txt
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/python/requirements.lock.txt
index e0a4d787..3e6b1e22 100644
--- a/bentoml/bentos/gemma2/27b-instruct-fp16-c398/env/python/requirements.lock.txt
+++ b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/python/requirements.lock.txt
@@ -77,7 +77,7 @@ nvidia-ml-py==11.525.150
 nvidia-nccl-cu12==2.20.5
 nvidia-nvjitlink-cu12==12.6.68
 nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
+openai==1.50.1
 opentelemetry-api==1.20.0
 opentelemetry-instrumentation==0.41b0
 opentelemetry-instrumentation-aiohttp-client==0.41b0
@@ -141,8 +141,8 @@ triton==3.0.0
 typing-extensions==4.12.2
 tzdata==2024.2
 urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
+uv==0.4.17
+uvicorn==0.31.0
 uvloop==0.20.0
 vllm==0.6.2
 watchfiles==0.24.0
@@ -152,5 +152,5 @@ wrapt==1.16.0
 wsproto==1.2.0
 xformers==0.0.27.post2
 xxhash==3.5.0
-yarl==1.13.0
+yarl==1.13.1
 zipp==3.20.2
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/python/requirements.txt b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/python/requirements.txt
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/python/requirements.txt
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/python/version.txt b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/env/python/version.txt
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/env/python/version.txt
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/bentofile.yaml b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/bentofile.yaml
similarity index 96%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/bentofile.yaml
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/bentofile.yaml
index 7ec17909..00035c76 100644
--- a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/bentofile.yaml
+++ b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/bentofile.yaml
@@ -1,6 +1,7 @@
 envs:
 - name: VLLM_ATTENTION_BACKEND
   value: FLASHINFER
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/openllm_config.yaml b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/openllm_config.yaml
similarity index 96%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/openllm_config.yaml
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/openllm_config.yaml
index 3fc7442f..a7c28e24 100644
--- a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/openllm_config.yaml
+++ b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/openllm_config.yaml
@@ -5,6 +5,7 @@ engine_config:
 extra_envs:
 - name: VLLM_ATTENTION_BACKEND
   value: FLASHINFER
+- name: HF_TOKEN
 extra_labels:
   model_name: google/gemma-2-9b-it
   openllm_alias: 9b,9b-instruct
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/service.py b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/service.py
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/service.py
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/service.py
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/404.html b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/404.html
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/404.html
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/apple-touch-icon.png b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/apple-touch-icon.png
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/chat.html b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/chat.html
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/chat.html
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/chat.txt b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/chat.txt
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/chat.txt
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/favicon-16x16.png b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/favicon-16x16.png
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/favicon.ico b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/favicon.ico
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/favicon.ico
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/index.html b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/index.html
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/index.html
diff --git a/bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/index.txt b/bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/gemma2/9b-instruct-fp16-3101/src/ui/index.txt
rename to bentoml/bentos/gemma2/9b-instruct-fp16-e0c2/src/ui/index.txt
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/README.md b/bentoml/bentos/llama2/13b-chat-fp16-01e5/README.md
similarity index 97%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/README.md
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/README.md
index d0de2037..442466a7 100644
--- a/bentoml/bentos/llama2/13b-chat-fp16-eb70/README.md
+++ b/bentoml/bentos/llama2/13b-chat-fp16-01e5/README.md
@@ -1,4 +1,4 @@
-# llama2:13b-chat-fp16-eb70
+# llama2:13b-chat-fp16-01e5
 
 [![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
 [![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/apis/openapi.yaml b/bentoml/bentos/llama2/13b-chat-fp16-01e5/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/apis/openapi.yaml
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/apis/openapi.yaml
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/apis/schema.json b/bentoml/bentos/llama2/13b-chat-fp16-01e5/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/apis/schema.json
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/apis/schema.json
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/bento.yaml b/bentoml/bentos/llama2/13b-chat-fp16-01e5/bento.yaml
similarity index 93%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/bento.yaml
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/bento.yaml
index 55daca93..9d53271d 100644
--- a/bentoml/bentos/llama2/13b-chat-fp16-eb70/bento.yaml
+++ b/bentoml/bentos/llama2/13b-chat-fp16-01e5/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama2
-version: 13b-chat-fp16-eb70
+version: 13b-chat-fp16-01e5
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:45:33.033938+00:00'
+creation_time: '2024-09-27T22:05:51.320921+00:00'
 labels:
   model_name: meta-llama/Llama-2-13b-chat-hf
   openllm_alias: 13b,13b-chat
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-tesla-a100
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama2
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/docker/Dockerfile b/bentoml/bentos/llama2/13b-chat-fp16-01e5/env/docker/Dockerfile
similarity index 98%
rename from bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/docker/Dockerfile
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/env/docker/Dockerfile
index 6a314dec..68790ac6 100644
--- a/bentoml/bentos/gemma/2b-instruct-fp16-9aec/env/docker/Dockerfile
+++ b/bentoml/bentos/llama2/13b-chat-fp16-01e5/env/docker/Dockerfile
@@ -34,6 +34,8 @@ ARG BENTO_USER=bentoml
 ARG BENTO_USER_UID=1034
 ARG BENTO_USER_GID=1034
 RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
 ARG BENTO_PATH=/home/bentoml/bento
 ENV BENTO_PATH=$BENTO_PATH
 ENV BENTOML_HOME=/home/bentoml/
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/env/docker/entrypoint.sh b/bentoml/bentos/llama2/13b-chat-fp16-01e5/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/env/docker/entrypoint.sh
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/env/python/install.sh b/bentoml/bentos/llama2/13b-chat-fp16-01e5/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/env/python/install.sh
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/env/python/install.sh
diff --git a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/python/requirements.lock.txt b/bentoml/bentos/llama2/13b-chat-fp16-01e5/env/python/requirements.lock.txt
similarity index 98%
rename from bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/python/requirements.lock.txt
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/env/python/requirements.lock.txt
index cf2d88c8..ed9d9aa3 100644
--- a/bentoml/bentos/codestral/22b-v0.1-fp16-0121/env/python/requirements.lock.txt
+++ b/bentoml/bentos/llama2/13b-chat-fp16-01e5/env/python/requirements.lock.txt
@@ -75,7 +75,7 @@ nvidia-ml-py==11.525.150
 nvidia-nccl-cu12==2.20.5
 nvidia-nvjitlink-cu12==12.6.68
 nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
+openai==1.50.1
 opentelemetry-api==1.20.0
 opentelemetry-instrumentation==0.41b0
 opentelemetry-instrumentation-aiohttp-client==0.41b0
@@ -139,8 +139,8 @@ triton==3.0.0
 typing-extensions==4.12.2
 tzdata==2024.2
 urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
+uv==0.4.17
+uvicorn==0.31.0
 uvloop==0.20.0
 vllm==0.6.2
 watchfiles==0.24.0
@@ -150,5 +150,5 @@ wrapt==1.16.0
 wsproto==1.2.0
 xformers==0.0.27.post2
 xxhash==3.5.0
-yarl==1.13.0
+yarl==1.13.1
 zipp==3.20.2
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/env/python/requirements.txt b/bentoml/bentos/llama2/13b-chat-fp16-01e5/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/env/python/requirements.txt
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/env/python/requirements.txt
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/env/python/version.txt b/bentoml/bentos/llama2/13b-chat-fp16-01e5/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/env/python/version.txt
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/env/python/version.txt
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/bentofile.yaml b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/bentofile.yaml
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/bentofile.yaml
index cced04ee..f99016d5 100644
--- a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/bentofile.yaml
+++ b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/openllm_config.yaml b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/openllm_config.yaml
similarity index 92%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/openllm_config.yaml
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/openllm_config.yaml
index a3772792..1781f68d 100644
--- a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/openllm_config.yaml
+++ b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/openllm_config.yaml
@@ -3,6 +3,8 @@ engine_config:
   dtype: half
   max_model_len: 1024
   model: meta-llama/Llama-2-13b-chat-hf
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Llama-2-13b-chat-hf
   openllm_alias: 13b,13b-chat
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/service.py b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/service.py
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/service.py
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/service.py
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/404.html b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/404.html
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/404.html
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/apple-touch-icon.png b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/chat.html b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/chat.html
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/chat.html
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/chat.txt b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/chat.txt
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/chat.txt
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/favicon-16x16.png b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/favicon.ico b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/favicon.ico
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/index.html b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/index.html
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/index.html
diff --git a/bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/index.txt b/bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama2/13b-chat-fp16-eb70/src/ui/index.txt
rename to bentoml/bentos/llama2/13b-chat-fp16-01e5/src/ui/index.txt
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/docker/Dockerfile b/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/python/requirements.lock.txt b/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/README.md b/bentoml/bentos/llama2/70b-chat-fp16-fb96/README.md
similarity index 97%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/README.md
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/README.md
index 902d52a9..6f7936e2 100644
--- a/bentoml/bentos/llama2/70b-chat-fp16-ab95/README.md
+++ b/bentoml/bentos/llama2/70b-chat-fp16-fb96/README.md
@@ -1,4 +1,4 @@
-# llama2:70b-chat-fp16-ab95
+# llama2:70b-chat-fp16-fb96
 
 [![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
 [![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/apis/openapi.yaml b/bentoml/bentos/llama2/70b-chat-fp16-fb96/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/apis/openapi.yaml
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/apis/openapi.yaml
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/apis/schema.json b/bentoml/bentos/llama2/70b-chat-fp16-fb96/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/apis/schema.json
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/apis/schema.json
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/bento.yaml b/bentoml/bentos/llama2/70b-chat-fp16-fb96/bento.yaml
similarity index 93%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/bento.yaml
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/bento.yaml
index fbb05216..317243dd 100644
--- a/bentoml/bentos/llama2/70b-chat-fp16-ab95/bento.yaml
+++ b/bentoml/bentos/llama2/70b-chat-fp16-fb96/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama2
-version: 70b-chat-fp16-ab95
+version: 70b-chat-fp16-fb96
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:45:38.621359+00:00'
+creation_time: '2024-09-27T22:05:56.039599+00:00'
 labels:
   model_name: meta-llama/Llama-2-70b-chat-hf
   openllm_alias: 70b,70b-chat
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-a100-80g
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama2
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/docker/Dockerfile b/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/docker/entrypoint.sh b/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/env/docker/entrypoint.sh
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/python/install.sh b/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/env/python/install.sh
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/env/python/install.sh
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/python/requirements.lock.txt b/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/python/requirements.txt b/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/env/python/requirements.txt
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/env/python/requirements.txt
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/env/python/version.txt b/bentoml/bentos/llama2/70b-chat-fp16-fb96/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/env/python/version.txt
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/env/python/version.txt
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/bentofile.yaml b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/bentofile.yaml
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/bentofile.yaml
index de9ea22b..aff89c98 100644
--- a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/bentofile.yaml
+++ b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/openllm_config.yaml b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/openllm_config.yaml
similarity index 92%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/openllm_config.yaml
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/openllm_config.yaml
index 9ec98f29..025d491f 100644
--- a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/openllm_config.yaml
+++ b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/openllm_config.yaml
@@ -4,6 +4,8 @@ engine_config:
   max_model_len: 1024
   model: meta-llama/Llama-2-70b-chat-hf
   tensor_parallel_size: 2
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Llama-2-70b-chat-hf
   openllm_alias: 70b,70b-chat
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/service.py b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/service.py
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/service.py
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/service.py
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/404.html b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/404.html
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/404.html
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/apple-touch-icon.png b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/chat.html b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/chat.html
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/chat.html
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/chat.txt b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/chat.txt
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/chat.txt
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/favicon-16x16.png b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/favicon.ico b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/favicon.ico
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/index.html b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/index.html
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/index.html
diff --git a/bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/index.txt b/bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama2/70b-chat-fp16-ab95/src/ui/index.txt
rename to bentoml/bentos/llama2/70b-chat-fp16-fb96/src/ui/index.txt
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/docker/Dockerfile b/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/python/requirements.lock.txt b/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/README.md b/bentoml/bentos/llama2/7b-chat-fp16-d7da/README.md
similarity index 97%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/README.md
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/README.md
index 9ecf823a..8540d75e 100644
--- a/bentoml/bentos/llama2/7b-chat-fp16-02a7/README.md
+++ b/bentoml/bentos/llama2/7b-chat-fp16-d7da/README.md
@@ -1,4 +1,4 @@
-# llama2:7b-chat-fp16-02a7
+# llama2:7b-chat-fp16-d7da
 
 [![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
 [![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/apis/openapi.yaml b/bentoml/bentos/llama2/7b-chat-fp16-d7da/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/apis/openapi.yaml
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/apis/openapi.yaml
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/apis/schema.json b/bentoml/bentos/llama2/7b-chat-fp16-d7da/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/apis/schema.json
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/apis/schema.json
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/bento.yaml b/bentoml/bentos/llama2/7b-chat-fp16-d7da/bento.yaml
similarity index 93%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/bento.yaml
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/bento.yaml
index 25f11169..1ca47559 100644
--- a/bentoml/bentos/llama2/7b-chat-fp16-02a7/bento.yaml
+++ b/bentoml/bentos/llama2/7b-chat-fp16-d7da/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama2
-version: 7b-chat-fp16-02a7
+version: 7b-chat-fp16-d7da
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:45:27.400310+00:00'
+creation_time: '2024-09-27T22:05:46.411833+00:00'
 labels:
   model_name: meta-llama/Llama-2-7b-chat-hf
   openllm_alias: 7b,7b-chat
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-tesla-t4
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama2
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/docker/Dockerfile b/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/docker/entrypoint.sh b/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/env/docker/entrypoint.sh
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/python/install.sh b/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/env/python/install.sh
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/env/python/install.sh
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/python/requirements.lock.txt b/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/python/requirements.txt b/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/env/python/requirements.txt
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/env/python/requirements.txt
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/env/python/version.txt b/bentoml/bentos/llama2/7b-chat-fp16-d7da/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/env/python/version.txt
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/env/python/version.txt
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/bentofile.yaml b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/bentofile.yaml
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/bentofile.yaml
index 6c841231..687b4c64 100644
--- a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/bentofile.yaml
+++ b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/openllm_config.yaml b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/openllm_config.yaml
similarity index 92%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/openllm_config.yaml
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/openllm_config.yaml
index e9fcf90d..1057f302 100644
--- a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/openllm_config.yaml
+++ b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/openllm_config.yaml
@@ -3,6 +3,8 @@ engine_config:
   dtype: half
   max_model_len: 1024
   model: meta-llama/Llama-2-7b-chat-hf
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Llama-2-7b-chat-hf
   openllm_alias: 7b,7b-chat
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/service.py b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/service.py
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/service.py
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/service.py
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/404.html b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/404.html
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/404.html
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/apple-touch-icon.png b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/chat.html b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/chat.html
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/chat.html
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/chat.txt b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/chat.txt
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/chat.txt
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/favicon-16x16.png b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/favicon.ico b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/favicon.ico
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/index.html b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/index.html
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/index.html
diff --git a/bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/index.txt b/bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama2/7b-chat-fp16-02a7/src/ui/index.txt
rename to bentoml/bentos/llama2/7b-chat-fp16-d7da/src/ui/index.txt
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/README.md b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/README.md
new file mode 100644
index 00000000..42322300
--- /dev/null
+++ b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/README.md
@@ -0,0 +1,16 @@
+# llama3.1:70b-instruct-fp16-859e
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/apis/openapi.yaml b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/apis/openapi.yaml
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/apis/openapi.yaml
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/apis/schema.json b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/apis/schema.json
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/apis/schema.json
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/bento.yaml b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/bento.yaml
similarity index 93%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/bento.yaml
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/bento.yaml
index fc9d1658..de118cd1 100644
--- a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/bento.yaml
+++ b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama3.1
-version: 70b-instruct-fp16-99ea
+version: 70b-instruct-fp16-859e
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:47:09.401337+00:00'
+creation_time: '2024-09-27T22:06:42.247788+00:00'
 labels:
   model_name: meta-llama/Meta-Llama-3.1-70B-Instruct
   openllm_alias: 70b,70b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-a100-80g
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama3.1
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/docker/Dockerfile b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/docker/entrypoint.sh b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/docker/entrypoint.sh
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/python/install.sh b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/python/install.sh
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/python/install.sh
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/python/requirements.lock.txt b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/python/requirements.txt b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/python/requirements.txt
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/python/requirements.txt
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/python/version.txt b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/python/version.txt
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/env/python/version.txt
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/bentofile.yaml b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/bentofile.yaml
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/bentofile.yaml
index 705f1a10..716f2d31 100644
--- a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/bentofile.yaml
+++ b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/openllm_config.yaml b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/openllm_config.yaml
similarity index 92%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/openllm_config.yaml
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/openllm_config.yaml
index 72a445a0..13f31ff1 100644
--- a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/openllm_config.yaml
+++ b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/openllm_config.yaml
@@ -2,6 +2,8 @@ engine_config:
   max_model_len: 2048
   model: meta-llama/Meta-Llama-3.1-70B-Instruct
   tensor_parallel_size: 2
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Meta-Llama-3.1-70B-Instruct
   openllm_alias: 70b,70b-instruct
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/service.py b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/service.py
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/service.py
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/service.py
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/404.html b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/404.html
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/404.html
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/apple-touch-icon.png b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/chat.html b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/chat.html
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/chat.html
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/chat.txt b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/chat.txt
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/chat.txt
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/favicon-16x16.png b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/favicon.ico b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/favicon.ico
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/index.html b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/index.html
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/index.html
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/index.txt b/bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/src/ui/index.txt
rename to bentoml/bentos/llama3.1/70b-instruct-fp16-859e/src/ui/index.txt
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/README.md b/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/README.md
deleted file mode 100644
index 0d7ae183..00000000
--- a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# llama3.1:70b-instruct-fp16-99ea
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/docker/Dockerfile b/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/python/requirements.lock.txt b/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/llama3.1/70b-instruct-fp16-99ea/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/README.md b/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/README.md
deleted file mode 100644
index cdb3dc26..00000000
--- a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# llama3.1:8b-instruct-fp16-7795
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/docker/Dockerfile b/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/python/requirements.lock.txt b/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/README.md b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/README.md
new file mode 100644
index 00000000..e4e7161f
--- /dev/null
+++ b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/README.md
@@ -0,0 +1,16 @@
+# llama3.1:8b-instruct-fp16-79d3
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/apis/openapi.yaml b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/apis/openapi.yaml
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/apis/openapi.yaml
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/apis/schema.json b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/apis/schema.json
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/apis/schema.json
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/bento.yaml b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/bento.yaml
similarity index 93%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/bento.yaml
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/bento.yaml
index 7ca1230a..0c747ae3 100644
--- a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/bento.yaml
+++ b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama3.1
-version: 8b-instruct-fp16-7795
+version: 8b-instruct-fp16-79d3
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:46:57.960419+00:00'
+creation_time: '2024-09-27T22:06:37.589034+00:00'
 labels:
   model_name: meta-llama/Meta-Llama-3.1-8B-Instruct
   openllm_alias: 8b,8b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-tesla-l4
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama3.1
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/docker/Dockerfile b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/docker/entrypoint.sh b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/docker/entrypoint.sh
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/python/install.sh b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/python/install.sh
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/python/install.sh
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/python/requirements.lock.txt b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/python/requirements.txt b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/python/requirements.txt
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/python/requirements.txt
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/python/version.txt b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/env/python/version.txt
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/env/python/version.txt
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/bentofile.yaml b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/bentofile.yaml
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/bentofile.yaml
index 805a8e35..d84fd240 100644
--- a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/bentofile.yaml
+++ b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/openllm_config.yaml b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/openllm_config.yaml
similarity index 91%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/openllm_config.yaml
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/openllm_config.yaml
index eb744a75..681682dc 100644
--- a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/openllm_config.yaml
+++ b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/openllm_config.yaml
@@ -2,6 +2,8 @@ engine_config:
   dtype: half
   max_model_len: 2048
   model: meta-llama/Meta-Llama-3.1-8B-Instruct
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Meta-Llama-3.1-8B-Instruct
   openllm_alias: 8b,8b-instruct
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/service.py b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/service.py
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/service.py
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/service.py
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/404.html b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/404.html
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/404.html
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/apple-touch-icon.png b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/chat.html b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/chat.html
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/chat.html
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/chat.txt b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/chat.txt
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/chat.txt
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/favicon-16x16.png b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/favicon.ico b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/favicon.ico
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/index.html b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/index.html
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/index.html
diff --git a/bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/index.txt b/bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama3.1/8b-instruct-fp16-7795/src/ui/index.txt
rename to bentoml/bentos/llama3.1/8b-instruct-fp16-79d3/src/ui/index.txt
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-1459/README.md b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/README.md
new file mode 100644
index 00000000..c33f68fa
--- /dev/null
+++ b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/README.md
@@ -0,0 +1,16 @@
+# llama3.2:11b-vision-instruct-1459
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/apis/openapi.yaml b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/apis/openapi.yaml
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/apis/openapi.yaml
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/apis/schema.json b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/apis/schema.json
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/apis/schema.json
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/bento.yaml b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/bento.yaml
similarity index 92%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/bento.yaml
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/bento.yaml
index 74537fae..4eb24789 100644
--- a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/bento.yaml
+++ b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama3.2
-version: 11b-vision-instruct-580b
+version: 11b-vision-instruct-1459
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:50:32.422389+00:00'
+creation_time: '2024-09-27T22:07:31.594186+00:00'
 labels:
   model_name: meta-llama/Llama-3.2-11B-Vision-Instruct
   openllm_alias: 11b-vision
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-a100-80gb
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama3.2
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/docker/Dockerfile b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/docker/entrypoint.sh b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/docker/entrypoint.sh
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/python/install.sh b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/python/install.sh
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/python/install.sh
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/python/requirements.lock.txt b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/python/requirements.txt b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/python/requirements.txt
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/python/requirements.txt
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/python/version.txt b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/python/version.txt
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/env/python/version.txt
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/bentofile.yaml b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/bentofile.yaml
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/bentofile.yaml
index 17034934..d9dd0b01 100644
--- a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/bentofile.yaml
+++ b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/openllm_config.yaml b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/openllm_config.yaml
similarity index 93%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/openllm_config.yaml
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/openllm_config.yaml
index d0af225e..45e7859f 100644
--- a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/openllm_config.yaml
+++ b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/openllm_config.yaml
@@ -5,6 +5,8 @@ engine_config:
   max_model_len: 16384
   max_num_seqs: 16
   model: meta-llama/Llama-3.2-11B-Vision-Instruct
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Llama-3.2-11B-Vision-Instruct
   openllm_alias: 11b-vision
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/service.py b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/service.py
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/service.py
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/service.py
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/404.html b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/404.html
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/404.html
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/apple-touch-icon.png b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/chat.html b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/chat.html
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/chat.html
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/chat.txt b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/chat.txt
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/chat.txt
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/favicon-16x16.png b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/favicon.ico b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/favicon.ico
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/index.html b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/index.html
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/index.html
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/index.txt b/bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/11b-vision-instruct-580b/src/ui/index.txt
rename to bentoml/bentos/llama3.2/11b-vision-instruct-1459/src/ui/index.txt
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/README.md b/bentoml/bentos/llama3.2/11b-vision-instruct-580b/README.md
deleted file mode 100644
index 7e6d9c5a..00000000
--- a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# llama3.2:11b-vision-instruct-580b
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/docker/Dockerfile b/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/python/requirements.lock.txt b/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/llama3.2/11b-vision-instruct-580b/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/README.md b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/README.md
new file mode 100644
index 00000000..f400a55b
--- /dev/null
+++ b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/README.md
@@ -0,0 +1,16 @@
+# llama3.2:1b-instruct-fp16-dc66
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/apis/openapi.yaml b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/apis/openapi.yaml
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/apis/openapi.yaml
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/apis/schema.json b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/apis/schema.json
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/apis/schema.json
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/bento.yaml b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/bento.yaml
similarity index 93%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/bento.yaml
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/bento.yaml
index 66401938..c6e223e8 100644
--- a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/bento.yaml
+++ b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama3.2
-version: 1b-instruct-fp16-ff3e
+version: 1b-instruct-fp16-dc66
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:46:46.695299+00:00'
+creation_time: '2024-09-27T22:06:28.359559+00:00'
 labels:
   model_name: meta-llama/Llama-3.2-1B-Instruct
   openllm_alias: 1b,1b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-rtx-3060
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama3.2
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/docker/Dockerfile b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/docker/entrypoint.sh b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/docker/entrypoint.sh
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/python/install.sh b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/python/install.sh
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/python/install.sh
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/python/requirements.lock.txt b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/python/requirements.txt b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/python/requirements.txt
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/python/requirements.txt
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/python/version.txt b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/python/version.txt
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/env/python/version.txt
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/bentofile.yaml b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/bentofile.yaml
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/bentofile.yaml
index e8368eee..45f549e1 100644
--- a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/bentofile.yaml
+++ b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/openllm_config.yaml b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/openllm_config.yaml
similarity index 91%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/openllm_config.yaml
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/openllm_config.yaml
index 9854d25f..976b7d96 100644
--- a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/openllm_config.yaml
+++ b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/openllm_config.yaml
@@ -2,6 +2,8 @@ engine_config:
   dtype: half
   max_model_len: 2048
   model: meta-llama/Llama-3.2-1B-Instruct
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Llama-3.2-1B-Instruct
   openllm_alias: 1b,1b-instruct
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/service.py b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/service.py
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/service.py
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/service.py
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/404.html b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/404.html
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/404.html
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/apple-touch-icon.png b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/chat.html b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/chat.html
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/chat.html
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/chat.txt b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/chat.txt
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/chat.txt
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/favicon-16x16.png b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/favicon.ico b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/favicon.ico
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/index.html b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/index.html
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/index.html
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/index.txt b/bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/src/ui/index.txt
rename to bentoml/bentos/llama3.2/1b-instruct-fp16-dc66/src/ui/index.txt
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/README.md b/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/README.md
deleted file mode 100644
index 4748ee44..00000000
--- a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# llama3.2:1b-instruct-fp16-ff3e
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/docker/Dockerfile b/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/python/requirements.lock.txt b/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/llama3.2/1b-instruct-fp16-ff3e/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/README.md b/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/README.md
deleted file mode 100644
index 40fef15a..00000000
--- a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# llama3.2:3b-instruct-fp16-47f0
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/docker/Dockerfile b/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/python/requirements.lock.txt b/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/README.md b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/README.md
new file mode 100644
index 00000000..d0d9eaa6
--- /dev/null
+++ b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/README.md
@@ -0,0 +1,16 @@
+# llama3.2:3b-instruct-fp16-6cc3
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/apis/openapi.yaml b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/apis/openapi.yaml
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/apis/openapi.yaml
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/apis/schema.json b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/apis/schema.json
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/apis/schema.json
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/bento.yaml b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/bento.yaml
similarity index 93%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/bento.yaml
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/bento.yaml
index 12028729..97d2118d 100644
--- a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/bento.yaml
+++ b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama3.2
-version: 3b-instruct-fp16-47f0
+version: 3b-instruct-fp16-6cc3
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:46:52.314522+00:00'
+creation_time: '2024-09-27T22:06:32.974977+00:00'
 labels:
   model_name: meta-llama/Llama-3.2-3B-Instruct
   openllm_alias: 3b,3b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-rtx-3060
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama3.2
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/docker/Dockerfile b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/docker/entrypoint.sh b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/docker/entrypoint.sh
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/python/install.sh b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/python/install.sh
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/python/install.sh
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/python/requirements.lock.txt b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/python/requirements.txt b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/python/requirements.txt
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/python/requirements.txt
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/python/version.txt b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/env/python/version.txt
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/env/python/version.txt
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/bentofile.yaml b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/bentofile.yaml
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/bentofile.yaml
index ea7822b6..1b60ba92 100644
--- a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/bentofile.yaml
+++ b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/openllm_config.yaml b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/openllm_config.yaml
similarity index 91%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/openllm_config.yaml
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/openllm_config.yaml
index acb8cf6b..b1c13f20 100644
--- a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/openllm_config.yaml
+++ b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/openllm_config.yaml
@@ -2,6 +2,8 @@ engine_config:
   dtype: half
   max_model_len: 2048
   model: meta-llama/Llama-3.2-3B-Instruct
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Llama-3.2-3B-Instruct
   openllm_alias: 3b,3b-instruct
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/service.py b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/service.py
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/service.py
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/service.py
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/404.html b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/404.html
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/404.html
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/apple-touch-icon.png b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/chat.html b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/chat.html
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/chat.html
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/chat.txt b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/chat.txt
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/chat.txt
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/favicon-16x16.png b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/favicon.ico b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/favicon.ico
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/index.html b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/index.html
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/index.html
diff --git a/bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/index.txt b/bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama3.2/3b-instruct-fp16-47f0/src/ui/index.txt
rename to bentoml/bentos/llama3.2/3b-instruct-fp16-6cc3/src/ui/index.txt
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/README.md b/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/README.md
deleted file mode 100644
index 3bf3f69c..00000000
--- a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# llama3:70b-instruct-fp16-3cbc
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/docker/Dockerfile b/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/python/requirements.lock.txt b/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-571d/README.md b/bentoml/bentos/llama3/70b-instruct-fp16-571d/README.md
new file mode 100644
index 00000000..434f318d
--- /dev/null
+++ b/bentoml/bentos/llama3/70b-instruct-fp16-571d/README.md
@@ -0,0 +1,16 @@
+# llama3:70b-instruct-fp16-571d
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/apis/openapi.yaml b/bentoml/bentos/llama3/70b-instruct-fp16-571d/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/apis/openapi.yaml
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/apis/openapi.yaml
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/apis/schema.json b/bentoml/bentos/llama3/70b-instruct-fp16-571d/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/apis/schema.json
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/apis/schema.json
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/bento.yaml b/bentoml/bentos/llama3/70b-instruct-fp16-571d/bento.yaml
similarity index 93%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/bento.yaml
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/bento.yaml
index 33c37216..1bda3c31 100644
--- a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/bento.yaml
+++ b/bentoml/bentos/llama3/70b-instruct-fp16-571d/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama3
-version: 70b-instruct-fp16-3cbc
+version: 70b-instruct-fp16-571d
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:46:41.061089+00:00'
+creation_time: '2024-09-27T22:06:23.780858+00:00'
 labels:
   model_name: meta-llama/Meta-Llama-3-70B-Instruct
   openllm_alias: 70b,70b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-a100-80g
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama3
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/docker/Dockerfile b/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/docker/entrypoint.sh b/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/docker/entrypoint.sh
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/python/install.sh b/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/python/install.sh
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/env/python/install.sh
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/python/requirements.lock.txt b/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/python/requirements.txt b/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/python/requirements.txt
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/env/python/requirements.txt
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/python/version.txt b/bentoml/bentos/llama3/70b-instruct-fp16-571d/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/env/python/version.txt
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/env/python/version.txt
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/bentofile.yaml b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/bentofile.yaml
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/bentofile.yaml
index 714698ac..d367dbb9 100644
--- a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/bentofile.yaml
+++ b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/openllm_config.yaml b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/openllm_config.yaml
similarity index 92%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/openllm_config.yaml
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/openllm_config.yaml
index 40b1fcd2..ad512d67 100644
--- a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/openllm_config.yaml
+++ b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/openllm_config.yaml
@@ -2,6 +2,8 @@ engine_config:
   max_model_len: 2048
   model: meta-llama/Meta-Llama-3-70B-Instruct
   tensor_parallel_size: 2
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Meta-Llama-3-70B-Instruct
   openllm_alias: 70b,70b-instruct
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/service.py b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/service.py
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/service.py
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/service.py
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/404.html b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/404.html
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/404.html
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/apple-touch-icon.png b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/chat.html b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/chat.html
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/chat.html
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/chat.txt b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/chat.txt
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/chat.txt
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/favicon-16x16.png b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/favicon.ico b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/favicon.ico
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/index.html b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/index.html
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/index.html
diff --git a/bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/index.txt b/bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama3/70b-instruct-fp16-3cbc/src/ui/index.txt
rename to bentoml/bentos/llama3/70b-instruct-fp16-571d/src/ui/index.txt
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/README.md b/bentoml/bentos/llama3/8b-instruct-fp16-2d07/README.md
deleted file mode 100644
index f67855cc..00000000
--- a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# llama3:8b-instruct-fp16-2d07
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/docker/Dockerfile b/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/python/requirements.lock.txt b/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-c11d/README.md b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/README.md
new file mode 100644
index 00000000..606c9b3b
--- /dev/null
+++ b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/README.md
@@ -0,0 +1,16 @@
+# llama3:8b-instruct-fp16-c11d
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/apis/openapi.yaml b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/apis/openapi.yaml
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/apis/openapi.yaml
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/apis/schema.json b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/apis/schema.json
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/apis/schema.json
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/apis/schema.json
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/bento.yaml b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/bento.yaml
similarity index 93%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/bento.yaml
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/bento.yaml
index 5adac66b..89a03749 100644
--- a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/bento.yaml
+++ b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: llama3
-version: 8b-instruct-fp16-2d07
+version: 8b-instruct-fp16-c11d
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:46:35.357596+00:00'
+creation_time: '2024-09-27T22:06:19.234759+00:00'
 labels:
   model_name: meta-llama/Meta-Llama-3-8B-Instruct
   openllm_alias: 8b,8b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-tesla-l4
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: llama3
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/docker/Dockerfile b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/docker/entrypoint.sh b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/docker/entrypoint.sh
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/python/install.sh b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/python/install.sh
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/python/install.sh
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/python/requirements.lock.txt b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/python/requirements.txt b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/python/requirements.txt
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/python/requirements.txt
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/python/version.txt b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/env/python/version.txt
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/env/python/version.txt
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/bentofile.yaml b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/bentofile.yaml
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/bentofile.yaml
index e99fac41..63f9b984 100644
--- a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/bentofile.yaml
+++ b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/openllm_config.yaml b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/openllm_config.yaml
similarity index 91%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/openllm_config.yaml
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/openllm_config.yaml
index 3da612d0..793b530a 100644
--- a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/openllm_config.yaml
+++ b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/openllm_config.yaml
@@ -2,6 +2,8 @@ engine_config:
   dtype: half
   max_model_len: 2048
   model: meta-llama/Meta-Llama-3-8B-Instruct
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: meta-llama/Meta-Llama-3-8B-Instruct
   openllm_alias: 8b,8b-instruct
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/service.py b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/service.py
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/service.py
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/service.py
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/404.html b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/404.html
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/404.html
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/apple-touch-icon.png b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/apple-touch-icon.png
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/chat.html b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/chat.html
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/chat.html
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/chat.txt b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/chat.txt
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/chat.txt
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/favicon-16x16.png b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/favicon-16x16.png
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/favicon.ico b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/favicon.ico
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/favicon.ico
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/index.html b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/index.html
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/index.html
diff --git a/bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/index.txt b/bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/llama3/8b-instruct-fp16-2d07/src/ui/index.txt
rename to bentoml/bentos/llama3/8b-instruct-fp16-c11d/src/ui/index.txt
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/README.md b/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/README.md
deleted file mode 100644
index 723c25f5..00000000
--- a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# mistral-large:123b-instruct-fp16-1564
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/docker/Dockerfile b/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/python/requirements.lock.txt b/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/README.md b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/README.md
new file mode 100644
index 00000000..83ef8bb3
--- /dev/null
+++ b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/README.md
@@ -0,0 +1,16 @@
+# mistral-large:123b-instruct-fp16-dd43
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/apis/openapi.yaml b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/apis/openapi.yaml
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/apis/openapi.yaml
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/apis/schema.json b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/apis/schema.json
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/apis/schema.json
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/apis/schema.json
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/bento.yaml b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/bento.yaml
similarity index 93%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/bento.yaml
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/bento.yaml
index 06fcdaaa..c5e64198 100644
--- a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/bento.yaml
+++ b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: mistral-large
-version: 123b-instruct-fp16-1564
+version: 123b-instruct-fp16-dd43
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:46:12.634603+00:00'
+creation_time: '2024-09-27T22:06:14.603498+00:00'
 labels:
   model_name: mistralai/Mistral-Large-Instruct-2407
   openllm_alias: 123b, 123b-instruct-2407
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-a100-80g
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: mistral-large
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/docker/Dockerfile b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/docker/entrypoint.sh b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/docker/entrypoint.sh
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/python/install.sh b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/python/install.sh
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/python/install.sh
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/python/requirements.lock.txt b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/python/requirements.txt b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/python/requirements.txt
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/python/requirements.txt
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/python/version.txt b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/env/python/version.txt
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/env/python/version.txt
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/bentofile.yaml b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/bentofile.yaml
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/bentofile.yaml
index faba5210..eb23c489 100644
--- a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/bentofile.yaml
+++ b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/openllm_config.yaml b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/openllm_config.yaml
similarity index 93%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/openllm_config.yaml
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/openllm_config.yaml
index 08d6bcb1..cc1460cd 100644
--- a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/openllm_config.yaml
+++ b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/openllm_config.yaml
@@ -4,6 +4,8 @@ engine_config:
   max_model_len: 2048
   model: mistralai/Mistral-Large-Instruct-2407
   tensor_parallel_size: 4
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: mistralai/Mistral-Large-Instruct-2407
   openllm_alias: 123b, 123b-instruct-2407
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/service.py b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/service.py
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/service.py
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/service.py
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/404.html b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/404.html
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/404.html
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/apple-touch-icon.png b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/apple-touch-icon.png
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/chat.html b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/chat.html
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/chat.html
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/chat.txt b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/chat.txt
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/chat.txt
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/favicon-16x16.png b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/favicon-16x16.png
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/favicon.ico b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/favicon.ico
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/favicon.ico
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/index.html b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/index.html
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/index.html
diff --git a/bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/index.txt b/bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/mistral-large/123b-instruct-fp16-1564/src/ui/index.txt
rename to bentoml/bentos/mistral-large/123b-instruct-fp16-dd43/src/ui/index.txt
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9505/README.md b/bentoml/bentos/mistral/24b-instruct-nemo-9505/README.md
new file mode 100644
index 00000000..6751b72e
--- /dev/null
+++ b/bentoml/bentos/mistral/24b-instruct-nemo-9505/README.md
@@ -0,0 +1,16 @@
+# mistral:24b-instruct-nemo-9505
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/apis/openapi.yaml b/bentoml/bentos/mistral/24b-instruct-nemo-9505/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/apis/openapi.yaml
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/apis/openapi.yaml
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/apis/schema.json b/bentoml/bentos/mistral/24b-instruct-nemo-9505/apis/schema.json
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/apis/schema.json
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/apis/schema.json
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/bento.yaml b/bentoml/bentos/mistral/24b-instruct-nemo-9505/bento.yaml
similarity index 93%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/bento.yaml
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/bento.yaml
index ce034d95..27983261 100644
--- a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/bento.yaml
+++ b/bentoml/bentos/mistral/24b-instruct-nemo-9505/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: mistral
-version: 24b-instruct-nemo-9d51
+version: 24b-instruct-nemo-9505
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:46:01.308085+00:00'
+creation_time: '2024-09-27T22:06:05.381380+00:00'
 labels:
   model_name: mistralai/Mistral-Nemo-Instruct-2407
   openllm_alias: nemo,nemo-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-a100-80g
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: mistral
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/docker/Dockerfile b/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/docker/entrypoint.sh b/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/docker/entrypoint.sh
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/python/install.sh b/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/python/install.sh
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/env/python/install.sh
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/python/requirements.lock.txt b/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/python/requirements.txt b/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/python/requirements.txt
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/env/python/requirements.txt
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/python/version.txt b/bentoml/bentos/mistral/24b-instruct-nemo-9505/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/python/version.txt
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/env/python/version.txt
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/bentofile.yaml b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/bentofile.yaml
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/bentofile.yaml
index a2beb59b..5c283100 100644
--- a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/bentofile.yaml
+++ b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/openllm_config.yaml b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/openllm_config.yaml
similarity index 92%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/openllm_config.yaml
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/openllm_config.yaml
index 76a7f3e4..2a8e04e6 100644
--- a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/openllm_config.yaml
+++ b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/openllm_config.yaml
@@ -4,6 +4,8 @@ engine_config:
   enforce_eager: true
   max_model_len: 2048
   model: mistralai/Mistral-Nemo-Instruct-2407
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: mistralai/Mistral-Nemo-Instruct-2407
   openllm_alias: nemo,nemo-instruct
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/service.py b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/service.py
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/service.py
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/service.py
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/404.html b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/404.html
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/404.html
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/apple-touch-icon.png b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/apple-touch-icon.png
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/chat.html b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/chat.html
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/chat.html
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/chat.txt b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/chat.txt
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/chat.txt
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/favicon-16x16.png b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/favicon-16x16.png
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/favicon.ico b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/favicon.ico
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/favicon.ico
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/index.html b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/index.html
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/index.html
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/index.txt b/bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/mistral/24b-instruct-nemo-9d51/src/ui/index.txt
rename to bentoml/bentos/mistral/24b-instruct-nemo-9505/src/ui/index.txt
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/README.md b/bentoml/bentos/mistral/24b-instruct-nemo-9d51/README.md
deleted file mode 100644
index afd07988..00000000
--- a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# mistral:24b-instruct-nemo-9d51
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/docker/Dockerfile b/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/python/requirements.lock.txt b/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/mistral/24b-instruct-nemo-9d51/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-31e6/README.md b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/README.md
new file mode 100644
index 00000000..eb47e441
--- /dev/null
+++ b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/README.md
@@ -0,0 +1,16 @@
+# mistral:7b-instruct-fp16-31e6
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/apis/openapi.yaml b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/apis/openapi.yaml
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/apis/openapi.yaml
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/apis/schema.json b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/apis/schema.json
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/apis/schema.json
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/apis/schema.json
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/bento.yaml b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/bento.yaml
similarity index 93%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/bento.yaml
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/bento.yaml
index 7e8a1ea5..79930454 100644
--- a/bentoml/bentos/mistral/7b-instruct-fp16-f243/bento.yaml
+++ b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: mistral
-version: 7b-instruct-fp16-f243
+version: 7b-instruct-fp16-31e6
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:45:55.635908+00:00'
+creation_time: '2024-09-27T22:06:00.701374+00:00'
 labels:
   model_name: mistralai/Mistral-7B-Instruct-v0.1
   openllm_alias: 7b,7b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-tesla-l4
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: mistral
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/docker/Dockerfile b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/docker/entrypoint.sh b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/env/docker/entrypoint.sh
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/python/install.sh b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/env/python/install.sh
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/python/install.sh
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/python/requirements.lock.txt b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/python/requirements.txt b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/env/python/requirements.txt
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/python/requirements.txt
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/python/version.txt b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/env/python/version.txt
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/env/python/version.txt
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/bentofile.yaml b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/bentofile.yaml
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/bentofile.yaml
index 97e1a602..0aeab288 100644
--- a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/bentofile.yaml
+++ b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/openllm_config.yaml b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/openllm_config.yaml
similarity index 92%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/openllm_config.yaml
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/openllm_config.yaml
index 9e8765eb..462b446c 100644
--- a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/openllm_config.yaml
+++ b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/openllm_config.yaml
@@ -4,6 +4,8 @@ engine_config:
   enforce_eager: true
   max_model_len: 1024
   model: mistralai/Mistral-7B-Instruct-v0.1
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: mistralai/Mistral-7B-Instruct-v0.1
   openllm_alias: 7b,7b-instruct
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/service.py b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/service.py
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/service.py
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/service.py
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/404.html b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/404.html
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/404.html
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/apple-touch-icon.png b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/apple-touch-icon.png
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/chat.html b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/chat.html
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/chat.html
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/chat.txt b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/chat.txt
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/chat.txt
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/favicon-16x16.png b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/favicon-16x16.png
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/favicon.ico b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/favicon.ico
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/favicon.ico
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/index.html b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/index.html
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/index.html
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/index.txt b/bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/mistral/7b-instruct-fp16-f243/src/ui/index.txt
rename to bentoml/bentos/mistral/7b-instruct-fp16-31e6/src/ui/index.txt
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/README.md b/bentoml/bentos/mistral/7b-instruct-fp16-f243/README.md
deleted file mode 100644
index b59634a8..00000000
--- a/bentoml/bentos/mistral/7b-instruct-fp16-f243/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# mistral:7b-instruct-fp16-f243
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/docker/Dockerfile b/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/python/requirements.lock.txt b/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/mistral/7b-instruct-fp16-f243/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/README.md b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/README.md
new file mode 100644
index 00000000..a6481d2a
--- /dev/null
+++ b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/README.md
@@ -0,0 +1,16 @@
+# mixtral:8x7b-instruct-v0.1-fp16-9bac
+
+[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
+[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
+[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
+[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
+[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
+
+This is a Machine Learning Service created with BentoML.
+
+## Help
+
+* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
+* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
+* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
+* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/apis/openapi.yaml b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/apis/openapi.yaml
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/apis/openapi.yaml
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/apis/openapi.yaml
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/apis/schema.json b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/apis/schema.json
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/apis/schema.json
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/apis/schema.json
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/bento.yaml b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/bento.yaml
similarity index 92%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/bento.yaml
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/bento.yaml
index cc85166a..ea94c063 100644
--- a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/bento.yaml
+++ b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/bento.yaml
@@ -1,8 +1,8 @@
 service: service:VLLM
 name: mixtral
-version: 8x7b-instruct-v0.1-fp16-a97f
+version: 8x7b-instruct-v0.1-fp16-9bac
 bentoml_version: 1.3.7
-creation_time: '2024-09-27T09:48:17.088858+00:00'
+creation_time: '2024-09-27T22:07:26.311585+00:00'
 labels:
   model_name: mistralai/Mixtral-8x7B-Instruct-v0.1
   openllm_alias: 8x7b,8x7b-instruct
@@ -23,7 +23,9 @@ services:
       gpu_type: nvidia-a100-80g
     traffic:
       timeout: 300
-envs: []
+envs:
+- name: HF_TOKEN
+  value: ''
 schema:
   name: mixtral
   type: service
@@ -72,7 +74,8 @@ docker:
   distro: debian
   python_version: '3.9'
   cuda_version: null
-  env: null
+  env:
+    HF_TOKEN: ''
   system_packages: null
   setup_script: null
   base_image: null
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/docker/Dockerfile b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/docker/Dockerfile
new file mode 100644
index 00000000..68790ac6
--- /dev/null
+++ b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/docker/Dockerfile
@@ -0,0 +1,71 @@
+# ===========================================
+#
+# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
+#
+# ===========================================
+
+# Block SETUP_BENTO_BASE_IMAGE
+FROM python:3.9-slim as base-container
+
+ENV LANG=C.UTF-8
+
+ENV LC_ALL=C.UTF-8
+
+ENV PYTHONIOENCODING=UTF-8
+
+ENV PYTHONUNBUFFERED=1
+
+
+
+USER root
+
+ENV DEBIAN_FRONTEND=noninteractive
+RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
+RUN set -eux && \
+    apt-get update -y && \
+    apt-get install -q -y --no-install-recommends --allow-remove-essential \
+        ca-certificates gnupg2 bash build-essential curl 
+ENV UV_SYSTEM_PYTHON=1
+RUN curl -LO https://astral.sh/uv/install.sh && \
+    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
+
+# Block SETUP_BENTO_USER
+ARG BENTO_USER=bentoml
+ARG BENTO_USER_UID=1034
+ARG BENTO_USER_GID=1034
+RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
+ARG HF_TOKEN=
+ENV HF_TOKEN=$HF_TOKEN
+ARG BENTO_PATH=/home/bentoml/bento
+ENV BENTO_PATH=$BENTO_PATH
+ENV BENTOML_HOME=/home/bentoml/
+ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
+
+RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
+WORKDIR $BENTO_PATH
+
+
+# Block SETUP_BENTO_COMPONENTS
+
+RUN uv pip install torch==2.4.0 ; exit 0
+RUN uv pip install vllm==0.6.2 ; exit 0
+COPY --chown=bentoml:bentoml ./env/python ./env/python/
+# install python packages with install.sh
+RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
+COPY --chown=bentoml:bentoml . ./
+
+# Block SETUP_BENTO_ENTRYPOINT
+RUN rm -rf /var/lib/{apt,cache,log}
+# Default port for BentoServer
+EXPOSE 3000
+
+# Expose Prometheus port
+EXPOSE 3001
+
+RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
+
+USER bentoml
+
+ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
+
+
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/docker/entrypoint.sh b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/docker/entrypoint.sh
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/docker/entrypoint.sh
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/docker/entrypoint.sh
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/python/install.sh b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/python/install.sh
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/python/install.sh
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/python/install.sh
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/python/requirements.lock.txt b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/python/requirements.lock.txt
new file mode 100644
index 00000000..ed9d9aa3
--- /dev/null
+++ b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/python/requirements.lock.txt
@@ -0,0 +1,154 @@
+--index-url https://pypi.org/simple
+
+aiohappyeyeballs==2.4.2
+aiohttp==3.10.6
+aiosignal==1.3.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.0
+appdirs==1.4.4
+asgiref==3.8.1
+async-timeout==4.0.3
+attrs==24.2.0
+bentoml==1.3.7
+cattrs==23.1.2
+certifi==2024.8.30
+charset-normalizer==3.3.2
+circus==0.18.0
+click==8.1.7
+click-option-group==0.5.6
+cloudpickle==3.0.0
+datasets==2.14.4
+deepmerge==2.0
+deprecated==1.2.14
+dill==0.3.7
+diskcache==5.6.3
+distro==1.9.0
+einops==0.8.0
+exceptiongroup==1.2.2
+fastapi==0.115.0
+filelock==3.16.1
+frozenlist==1.4.1
+fs==2.4.16
+fsspec==2024.9.0
+gguf==0.10.0
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-ws==0.6.0
+huggingface-hub==0.25.1
+idna==3.10
+importlib-metadata==6.11.0
+inflection==0.5.1
+interegular==0.3.3
+jinja2==3.1.4
+jiter==0.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+lark==1.2.2
+llvmlite==0.43.0
+lm-format-enforcer==0.10.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+mdurl==0.1.2
+mistral-common==1.4.3
+mpmath==1.3.0
+msgpack==1.1.0
+msgspec==0.18.6
+multidict==6.1.0
+multiprocess==0.70.15
+nest-asyncio==1.6.0
+networkx==3.2.1
+numba==0.60.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-ml-py==11.525.150
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+openai==1.50.1
+opentelemetry-api==1.20.0
+opentelemetry-instrumentation==0.41b0
+opentelemetry-instrumentation-aiohttp-client==0.41b0
+opentelemetry-instrumentation-asgi==0.41b0
+opentelemetry-sdk==1.20.0
+opentelemetry-semantic-conventions==0.41b0
+opentelemetry-util-http==0.41b0
+outlines==0.0.46
+packaging==24.1
+pandas==2.2.3
+partial-json-parser==0.2.1.1.post4
+pathspec==0.12.1
+pillow==10.4.0
+pip-requirements-parser==32.0.1
+prometheus-client==0.21.0
+prometheus-fastapi-instrumentator==7.0.0
+prompt-toolkit==3.0.36
+protobuf==5.28.2
+psutil==6.0.0
+py-cpuinfo==9.0.0
+pyairports==2.1.1
+pyarrow==17.0.0
+pycountry==24.6.1
+pydantic==2.9.2
+pydantic-core==2.23.4
+pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==2.0.7
+python-multipart==0.0.10
+pytz==2024.2
+pyyaml==6.0.2
+pyzmq==26.2.0
+questionary==2.0.1
+ray==2.37.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
+safetensors==0.4.5
+schema==0.7.7
+sentencepiece==0.2.0
+setuptools==75.1.0
+simple-di==0.1.5
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+tomli-w==1.0.0
+torch==2.4.0
+torchvision==0.19.0
+tornado==6.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+typing-extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uv==0.4.17
+uvicorn==0.31.0
+uvloop==0.20.0
+vllm==0.6.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+xformers==0.0.27.post2
+xxhash==3.5.0
+yarl==1.13.1
+zipp==3.20.2
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/python/requirements.txt b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/python/requirements.txt
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/python/requirements.txt
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/python/requirements.txt
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/python/version.txt b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/python/version.txt
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/python/version.txt
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/env/python/version.txt
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/bentofile.yaml b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/bentofile.yaml
similarity index 94%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/bentofile.yaml
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/bentofile.yaml
index d42dd56a..ce23b10f 100644
--- a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/bentofile.yaml
+++ b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/bentofile.yaml
@@ -1,4 +1,5 @@
-envs: []
+envs:
+- name: HF_TOKEN
 include:
 - '*.py'
 - '*.yaml'
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/alpaca.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/alpaca.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/alpaca.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/alpaca.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/amberchat.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/amberchat.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/amberchat.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/amberchat.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/chatml.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/chatml.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/chatml.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/chatml.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/chatqa.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/chatqa.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/chatqa.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/chatqa.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/falcon-instruct.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/falcon-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/falcon-instruct.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/falcon-instruct.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/gemma-it.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/gemma-it.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/gemma-it.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/gemma-it.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/llama-2-chat.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/llama-2-chat.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/llama-2-chat.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/llama-2-chat.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/llama-3-chat.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/llama-3-chat.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/llama-3-chat.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/llama-3-chat.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/mistral-instruct.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/mistral-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/mistral-instruct.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/mistral-instruct.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/openchat.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/openchat.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/openchat.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/openchat.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/phi-3.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/phi-3.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/phi-3.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/phi-3.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/saiga.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/saiga.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/saiga.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/saiga.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/solar-instruct.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/solar-instruct.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/solar-instruct.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/solar-instruct.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/vicuna.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/vicuna.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/vicuna.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/vicuna.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/zephyr.jinja b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/zephyr.jinja
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/chat_templates/chat_templates/zephyr.jinja
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/chat_templates/chat_templates/zephyr.jinja
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/openllm_config.yaml b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/openllm_config.yaml
similarity index 92%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/openllm_config.yaml
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/openllm_config.yaml
index cb2aae58..24c74345 100644
--- a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/openllm_config.yaml
+++ b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/openllm_config.yaml
@@ -3,6 +3,8 @@ engine_config:
   max_model_len: 2048
   model: mistralai/Mixtral-8x7B-Instruct-v0.1
   tensor_parallel_size: 2
+extra_envs:
+- name: HF_TOKEN
 extra_labels:
   model_name: mistralai/Mixtral-8x7B-Instruct-v0.1
   openllm_alias: 8x7b,8x7b-instruct
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/service.py b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/service.py
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/service.py
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/service.py
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/404.html b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/404.html
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/404.html
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/404.html
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_buildManifest.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/UFSnOXBHq5ysU6-5BuENB/_ssgManifest.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/0e5ce63c-f5957df8d97fa48f.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/370b0802-87e84e603248538e.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/3d47b92a-f8bda4b39f1e2d9d.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/479ba886-0c92f49cb8e74e58.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/59650de3-87b10f0662b51900.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/66ec4792-34336521b476aa45.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/674-a1fcdac3696c5ed0.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/69-bf2efb63b1299e3b.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/700-532b1fe2415e5859.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/700-532b1fe2415e5859.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/899-fa939dd99dc7a1df.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/8e1d74a4-a6b9a2554f9153c0.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/94730671-0f73873f7f5896de.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/995-34374f39bb210839.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/995-34374f39bb210839.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/995-34374f39bb210839.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/995-34374f39bb210839.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/app/(site)/page-5b6e14439f55739b.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/app/chat/page-9c8e223f40771eb6.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/app/layout-df2dea9dba0ceb06.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/app/not-found-c76dccfb8b88da53.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/d3ac728e-0c798b3b8aa3bf53.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/fd9d1056-32c33f3919735051.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/framework-00a8ba1a63cfdc9e.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/main-app-e95f89b5006af8a8.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/main-bf1416cb53f2b4c0.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/pages/_app-d21e88acd55d90f1.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/pages/_error-d6107f1aac0c574c.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/chunks/webpack-ee8b17d5a5297ccd.js
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/css/429544bd3cd8ce3a.css b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/css/429544bd3cd8ce3a.css
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/css/429544bd3cd8ce3a.css
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/css/429544bd3cd8ce3a.css
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/css/5b67f082b31cfc7b.css b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/css/5b67f082b31cfc7b.css
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/css/5b67f082b31cfc7b.css
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/css/5b67f082b31cfc7b.css
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/css/9e63023b20ddb15e.css b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/css/9e63023b20ddb15e.css
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/_next/static/css/9e63023b20ddb15e.css
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/_next/static/css/9e63023b20ddb15e.css
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/apple-touch-icon.png b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/apple-touch-icon.png
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/apple-touch-icon.png
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/apple-touch-icon.png
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/chat.html b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/chat.html
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/chat.html
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/chat.html
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/chat.txt b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/chat.txt
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/chat.txt
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/chat.txt
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/favicon-16x16.png b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/favicon-16x16.png
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/favicon-16x16.png
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/favicon-16x16.png
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/favicon.ico b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/favicon.ico
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/favicon.ico
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/favicon.ico
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/index.html b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/index.html
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/index.html
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/index.html
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/index.txt b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/index.txt
similarity index 100%
rename from bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/src/ui/index.txt
rename to bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-9bac/src/ui/index.txt
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/README.md b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/README.md
deleted file mode 100644
index 96058d56..00000000
--- a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# mixtral:8x7b-instruct-v0.1-fp16-a97f
-
-[![pypi_status](https://img.shields.io/badge/BentoML-1.3.7-informational)](https://pypi.org/project/BentoML)
-[![documentation_status](https://readthedocs.org/projects/bentoml/badge/?version=latest)](https://docs.bentoml.com/)
-[![join_slack](https://badgen.net/badge/Join/BentoML%20Slack/cyan?icon=slack)](https://l.bentoml.com/join-slack-swagger)
-[![BentoML GitHub Repo](https://img.shields.io/github/stars/bentoml/bentoml?style=social)](https://github.com/bentoml/BentoML)
-[![Twitter Follow](https://img.shields.io/twitter/follow/bentomlai?label=Follow%20BentoML&style=social)](https://twitter.com/bentomlai)
-
-This is a Machine Learning Service created with BentoML.
-
-## Help
-
-* [📖 Documentation](https://docs.bentoml.com/en/latest/): Learn how to use BentoML.
-* [💬 Community](https://l.bentoml.com/join-slack-swagger): Join the BentoML Slack community.
-* [🐛 GitHub Issues](https://github.com/bentoml/BentoML/issues): Report bugs and feature requests.
-* Tip: you can also [customize this README](https://docs.bentoml.com/en/latest/concepts/bento.html#description).
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/docker/Dockerfile b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/docker/Dockerfile
deleted file mode 100644
index 6a314dec..00000000
--- a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/docker/Dockerfile
+++ /dev/null
@@ -1,69 +0,0 @@
-# ===========================================
-#
-# THIS IS A GENERATED DOCKERFILE. DO NOT EDIT
-#
-# ===========================================
-
-# Block SETUP_BENTO_BASE_IMAGE
-FROM python:3.9-slim as base-container
-
-ENV LANG=C.UTF-8
-
-ENV LC_ALL=C.UTF-8
-
-ENV PYTHONIOENCODING=UTF-8
-
-ENV PYTHONUNBUFFERED=1
-
-
-
-USER root
-
-ENV DEBIAN_FRONTEND=noninteractive
-RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
-RUN set -eux && \
-    apt-get update -y && \
-    apt-get install -q -y --no-install-recommends --allow-remove-essential \
-        ca-certificates gnupg2 bash build-essential curl 
-ENV UV_SYSTEM_PYTHON=1
-RUN curl -LO https://astral.sh/uv/install.sh && \
-    sh install.sh && rm install.sh && mv $HOME/.cargo/bin/uv /usr/local/bin/
-
-# Block SETUP_BENTO_USER
-ARG BENTO_USER=bentoml
-ARG BENTO_USER_UID=1034
-ARG BENTO_USER_GID=1034
-RUN groupadd -g $BENTO_USER_GID -o $BENTO_USER && useradd -m -u $BENTO_USER_UID -g $BENTO_USER_GID -o -r $BENTO_USER
-ARG BENTO_PATH=/home/bentoml/bento
-ENV BENTO_PATH=$BENTO_PATH
-ENV BENTOML_HOME=/home/bentoml/
-ENV BENTOML_HF_CACHE_DIR=/home/bentoml/bento/hf-models
-
-RUN mkdir $BENTO_PATH && chown bentoml:bentoml $BENTO_PATH -R
-WORKDIR $BENTO_PATH
-
-
-# Block SETUP_BENTO_COMPONENTS
-
-RUN uv pip install torch==2.4.0 ; exit 0
-RUN uv pip install vllm==0.6.2 ; exit 0
-COPY --chown=bentoml:bentoml ./env/python ./env/python/
-# install python packages with install.sh
-RUN bash -euxo pipefail /home/bentoml/bento/env/python/install.sh
-COPY --chown=bentoml:bentoml . ./
-
-# Block SETUP_BENTO_ENTRYPOINT
-RUN rm -rf /var/lib/{apt,cache,log}
-# Default port for BentoServer
-EXPOSE 3000
-
-# Expose Prometheus port
-EXPOSE 3001
-
-RUN chmod +x /home/bentoml/bento/env/docker/entrypoint.sh
-
-USER bentoml
-
-ENTRYPOINT [ "/home/bentoml/bento/env/docker/entrypoint.sh" ]
-
-
diff --git a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/python/requirements.lock.txt b/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/python/requirements.lock.txt
deleted file mode 100644
index cf2d88c8..00000000
--- a/bentoml/bentos/mixtral/8x7b-instruct-v0.1-fp16-a97f/env/python/requirements.lock.txt
+++ /dev/null
@@ -1,154 +0,0 @@
---index-url https://pypi.org/simple
-
-aiohappyeyeballs==2.4.2
-aiohttp==3.10.6
-aiosignal==1.3.1
-aiosqlite==0.20.0
-annotated-types==0.7.0
-anyio==4.6.0
-appdirs==1.4.4
-asgiref==3.8.1
-async-timeout==4.0.3
-attrs==24.2.0
-bentoml==1.3.7
-cattrs==23.1.2
-certifi==2024.8.30
-charset-normalizer==3.3.2
-circus==0.18.0
-click==8.1.7
-click-option-group==0.5.6
-cloudpickle==3.0.0
-datasets==2.14.4
-deepmerge==2.0
-deprecated==1.2.14
-dill==0.3.7
-diskcache==5.6.3
-distro==1.9.0
-einops==0.8.0
-exceptiongroup==1.2.2
-fastapi==0.115.0
-filelock==3.16.1
-frozenlist==1.4.1
-fs==2.4.16
-fsspec==2024.9.0
-gguf==0.10.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.2
-httpx-ws==0.6.0
-huggingface-hub==0.25.1
-idna==3.10
-importlib-metadata==6.11.0
-inflection==0.5.1
-interegular==0.3.3
-jinja2==3.1.4
-jiter==0.5.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-lark==1.2.2
-llvmlite==0.43.0
-lm-format-enforcer==0.10.6
-markdown-it-py==3.0.0
-markupsafe==2.1.5
-mdurl==0.1.2
-mistral-common==1.4.3
-mpmath==1.3.0
-msgpack==1.1.0
-msgspec==0.18.6
-multidict==6.1.0
-multiprocess==0.70.15
-nest-asyncio==1.6.0
-networkx==3.2.1
-numba==0.60.0
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-ml-py==11.525.150
-nvidia-nccl-cu12==2.20.5
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-openai==1.50.0
-opentelemetry-api==1.20.0
-opentelemetry-instrumentation==0.41b0
-opentelemetry-instrumentation-aiohttp-client==0.41b0
-opentelemetry-instrumentation-asgi==0.41b0
-opentelemetry-sdk==1.20.0
-opentelemetry-semantic-conventions==0.41b0
-opentelemetry-util-http==0.41b0
-outlines==0.0.46
-packaging==24.1
-pandas==2.2.3
-partial-json-parser==0.2.1.1.post4
-pathspec==0.12.1
-pillow==10.4.0
-pip-requirements-parser==32.0.1
-prometheus-client==0.21.0
-prometheus-fastapi-instrumentator==7.0.0
-prompt-toolkit==3.0.36
-protobuf==5.28.2
-psutil==6.0.0
-py-cpuinfo==9.0.0
-pyairports==2.1.1
-pyarrow==17.0.0
-pycountry==24.6.1
-pydantic==2.9.2
-pydantic-core==2.23.4
-pygments==2.18.0
-pyparsing==3.1.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-python-multipart==0.0.10
-pytz==2024.2
-pyyaml==6.0.2
-pyzmq==26.2.0
-questionary==2.0.1
-ray==2.37.0
-referencing==0.35.1
-regex==2024.9.11
-requests==2.32.3
-rich==13.8.1
-rpds-py==0.20.0
-safetensors==0.4.5
-schema==0.7.7
-sentencepiece==0.2.0
-setuptools==75.1.0
-simple-di==0.1.5
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.3
-tiktoken==0.7.0
-tokenizers==0.20.0
-tomli==2.0.1
-tomli-w==1.0.0
-torch==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-transformers==4.45.1
-triton==3.0.0
-typing-extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-uv==0.4.16
-uvicorn==0.30.6
-uvloop==0.20.0
-vllm==0.6.2
-watchfiles==0.24.0
-wcwidth==0.2.13
-websockets==13.1
-wrapt==1.16.0
-wsproto==1.2.0
-xformers==0.0.27.post2
-xxhash==3.5.0
-yarl==1.13.0
-zipp==3.20.2
diff --git a/src/recipe.yaml b/src/recipe.yaml
index 7cec2785..95c9fdce 100644
--- a/src/recipe.yaml
+++ b/src/recipe.yaml
@@ -24,6 +24,8 @@
     resources:
       gpu: 1
       gpu_type: nvidia-tesla-t4
+  extra_envs:
+    - name: HF_TOKEN
   engine_config:
     model: meta-llama/Llama-2-7b-chat-hf
     max_model_len: 1024
@@ -41,6 +43,8 @@
     resources:
       gpu: 1
       gpu_type: nvidia-tesla-a100
+  extra_envs:
+    - name: HF_TOKEN
   engine_config:
     model: meta-llama/Llama-2-13b-chat-hf
     max_model_len: 1024
@@ -58,6 +62,8 @@
     resources:
       gpu: 2
       gpu_type: nvidia-a100-80g
+  extra_envs:
+    - name: HF_TOKEN
   engine_config:
     model: meta-llama/Llama-2-70b-chat-hf
     max_model_len: 1024
@@ -118,6 +124,8 @@
     max_model_len: 1024
     enforce_eager: true
     dtype: half
+  extra_envs:
+    - name: HF_TOKEN
   chat_template: mistral-instruct
   extra_labels:
     openllm_alias: 7b,7b-instruct
@@ -137,6 +145,8 @@
     enforce_eager: true
     dtype: half
   chat_template: mistral-instruct
+  extra_envs:
+    - name: HF_TOKEN
   extra_labels:
     openllm_alias: nemo,nemo-instruct
     model_name: mistralai/Mistral-Nemo-Instruct-2407
@@ -155,6 +165,8 @@
     enforce_eager: true
     dtype: half
   chat_template: mistral-instruct
+  extra_envs:
+    - name: HF_TOKEN
   extra_labels:
     openllm_alias: 22b,22b-v0.1
     model_name: mistralai/Codestral-22B-v0.1
@@ -173,6 +185,8 @@
     dtype: half
     tensor_parallel_size: 4
   chat_template: mistral-instruct
+  extra_envs:
+    - name: HF_TOKEN
   extra_labels:
     openllm_alias: 123b, 123b-instruct-2407
     model_name: mistralai/Mistral-Large-Instruct-2407
@@ -238,6 +252,8 @@
     model: meta-llama/Meta-Llama-3-8B-Instruct
     max_model_len: 2048
     dtype: half
+  extra_envs:
+    - name: HF_TOKEN
   extra_labels:
     openllm_alias: 8b,8b-instruct
     model_name: meta-llama/Meta-Llama-3-8B-Instruct
@@ -254,6 +270,8 @@
     model: meta-llama/Meta-Llama-3-70B-Instruct
     max_model_len: 2048
     tensor_parallel_size: 2
+  extra_envs:
+    - name: HF_TOKEN
   extra_labels:
     openllm_alias: 70b,70b-instruct
     model_name: meta-llama/Meta-Llama-3-70B-Instruct
@@ -270,6 +288,8 @@
     model: meta-llama/Llama-3.2-1B-Instruct
     max_model_len: 2048
     dtype: half
+  extra_envs:
+    - name: HF_TOKEN
   extra_labels:
     openllm_alias: 1b,1b-instruct
     model_name: meta-llama/Llama-3.2-1B-Instruct
@@ -286,6 +306,8 @@
     model: meta-llama/Llama-3.2-3B-Instruct
     max_model_len: 2048
     dtype: half
+  extra_envs:
+    - name: HF_TOKEN
   extra_labels:
     openllm_alias: 3b,3b-instruct
     model_name: meta-llama/Llama-3.2-3B-Instruct
@@ -298,6 +320,8 @@
     resources:
       gpu: 1
       gpu_type: nvidia-tesla-l4
+  extra_envs:
+    - name: HF_TOKEN
   engine_config:
     model: meta-llama/Meta-Llama-3.1-8B-Instruct
     max_model_len: 2048
@@ -334,6 +358,8 @@
     model: meta-llama/Meta-Llama-3.1-70B-Instruct
     max_model_len: 2048
     tensor_parallel_size: 2
+  extra_envs:
+    - name: HF_TOKEN
   extra_labels:
     openllm_alias: 70b,70b-instruct
     model_name: meta-llama/Meta-Llama-3.1-70B-Instruct
@@ -389,6 +415,7 @@
   extra_envs:
     - name: VLLM_ATTENTION_BACKEND
       value: FLASHINFER
+    - name: HF_TOKEN
   extra_requirements:
     - --extra-index-url https://flashinfer.ai/whl/cu121/torch2.3
     - flashinfer==0.1.2+cu121torch2.3
@@ -411,6 +438,7 @@
   extra_envs:
     - name: VLLM_ATTENTION_BACKEND
       value: FLASHINFER
+    - name: HF_TOKEN
   extra_requirements:
     - --extra-index-url https://flashinfer.ai/whl/cu121/torch2.3
     - flashinfer==0.1.2+cu121torch2.3
@@ -430,6 +458,8 @@
   extra_labels:
     openllm_alias: 2b,2b-instruct
     model_name: google/gemma-2b-it
+  extra_envs:
+    - name: HF_TOKEN
 'gemma:7b-instruct-fp16':
   project: vllm-chat
   service_config:
@@ -446,6 +476,8 @@
   extra_labels:
     openllm_alias: 7b,7b-instruct
     model_name: google/gemma-7b-it
+  extra_envs:
+    - name: HF_TOKEN
 'gemma:7b-instruct-awq-4bit':
   project: vllm-chat
   service_config:
@@ -477,6 +509,8 @@
     max_model_len: 2048
     tensor_parallel_size: 2
   chat_template: mistral-instruct
+  extra_envs:
+    - name: HF_TOKEN
   extra_labels:
     openllm_alias: 8x7b,8x7b-instruct
     model_name: mistralai/Mixtral-8x7B-Instruct-v0.1
@@ -757,6 +791,8 @@
   extra_labels:
     openllm_alias: 11b-vision
     model_name: meta-llama/Llama-3.2-11B-Vision-Instruct
+  extra_envs:
+    - name: HF_TOKEN
 'pixtral:12b-240910':
   project: vllm-chat
   service_config: