Update README.md

bentoml · Jul 6, 2024 · e7bbd95 · e7bbd95
1 parent 8e1807e
commit e7bbd95
Showing 1 changed file with 34 additions and 21 deletions.
diff --git a/README.md b/README.md
@@ -12,6 +12,7 @@
 - [Qwen-2](#qwen2)
 - [Gemma](#gemma)
 - [Llama-2](#llama2)
+- [](#mixtral)
 
 ---
 
@@ -20,10 +21,10 @@
 
 | Model | Version | Huggingface Link |
 | --- | --- | --- |
-| llama3 | 70b-instruct-awq-4bit | [HF Link](https://huggingface.co/casperhansen/llama-3-70b-instruct-awq) |
-| llama3 | 70b-instruct-fp16 | [HF Link](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) |
-| llama3 | 8b-instruct-awq-4bit | [HF Link](https://huggingface.co/casperhansen/llama-3-8b-instruct-awq) |
-| llama3 | 8b-instruct-fp16 | [HF Link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) |
+| llama3 | 70b-instruct-awq-4bit-3948 | [HF Link](https://huggingface.co/casperhansen/llama-3-70b-instruct-awq) |
+| llama3 | 70b-instruct-fp16-8678 | [HF Link](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) |
+| llama3 | 8b-instruct-awq-4bit-f711 | [HF Link](https://huggingface.co/casperhansen/llama-3-8b-instruct-awq) |
+| llama3 | 8b-instruct-fp16-46f3 | [HF Link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) |
 
 ---
 
@@ -32,7 +33,8 @@
 
 | Model | Version | Huggingface Link |
 | --- | --- | --- |
-| phi3 | 3.8b-mini-instruct-4k-fp16 | [HF Link](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) |
+| phi3 | 3.8b-instruct-fp16-a912 | [HF Link](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) |
+| phi3 | 3.8b-instruct-ggml-q4-6139 | [HF Link](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf) |
 
 ---
 
@@ -41,8 +43,8 @@
 
 | Model | Version | Huggingface Link |
 | --- | --- | --- |
-| mistral | 7b-instruct-awq-4bit | [HF Link](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ) |
-| mistral | 7b-instruct-fp16 | [HF Link](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) |
+| mistral | 7b-instruct-awq-4bit-2a5e | [HF Link](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-AWQ) |
+| mistral | 7b-instruct-fp16-e205 | [HF Link](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) |
 
 ---
 
@@ -51,13 +53,13 @@
 
 | Model | Version | Huggingface Link |
 | --- | --- | --- |
-| qwen2 | 0.5b-instruct-fp16 | [HF Link](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) |
-| qwen2 | 1.5b-instruct-fp16 | [HF Link](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) |
-| qwen2 | 57b-a14b-instruct-fp16 | [HF Link](https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct) |
-| qwen2 | 72b-instruct-awq-4bit | [HF Link](https://huggingface.co/Qwen/Qwen2-72B-Instruct-AWQ) |
-| qwen2 | 72b-instruct-fp16 | [HF Link](https://huggingface.co/Qwen/Qwen2-72B-Instruct) |
-| qwen2 | 7b-instruct-awq-4bit | [HF Link](https://huggingface.co/Qwen/Qwen2-7B-Instruct-AWQ) |
-| qwen2 | 7b-instruct-fp16 | [HF Link](https://huggingface.co/Qwen/Qwen2-7B-Instruct) |
+| qwen2 | 0.5b-instruct-fp16-855c | [HF Link](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) |
+| qwen2 | 1.5b-instruct-fp16-3346 | [HF Link](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) |
+| qwen2 | 57b-a14b-instruct-fp16-8d40 | [HF Link](https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct) |
+| qwen2 | 72b-instruct-awq-4bit-177e | [HF Link](https://huggingface.co/Qwen/Qwen2-72B-Instruct-AWQ) |
+| qwen2 | 72b-instruct-fp16-e6e1 | [HF Link](https://huggingface.co/Qwen/Qwen2-72B-Instruct) |
+| qwen2 | 7b-instruct-awq-4bit-77be | [HF Link](https://huggingface.co/Qwen/Qwen2-7B-Instruct-AWQ) |
+| qwen2 | 7b-instruct-fp16-9381 | [HF Link](https://huggingface.co/Qwen/Qwen2-7B-Instruct) |
 
 ---
 
@@ -66,9 +68,9 @@
 
 | Model | Version | Huggingface Link |
 | --- | --- | --- |
-| gemma | 2b-instruct-fp16 | [HF Link](https://huggingface.co/google/gemma-2b-it) |
-| gemma | 7b-instruct-awq-4bit | [HF Link](https://huggingface.co/casperhansen/gemma-7b-it-awq) |
-| gemma | 7b-instruct-fp16 | [HF Link](https://huggingface.co/google/gemma-7b-it) |
+| gemma | 2b-instruct-fp16-da36 | [HF Link](https://huggingface.co/google/gemma-2b-it) |
+| gemma | 7b-instruct-awq-4bit-6a74 | [HF Link](https://huggingface.co/casperhansen/gemma-7b-it-awq) |
+| gemma | 7b-instruct-fp16-dafc | [HF Link](https://huggingface.co/google/gemma-7b-it) |
 
 ---
 
@@ -77,9 +79,20 @@
 
 | Model | Version | Huggingface Link |
 | --- | --- | --- |
-| llama2 | 13b-chat-fp16 | [HF Link](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) |
-| llama2 | 70b-chat-fp16 | [HF Link](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) |
-| llama2 | 7b-chat-awq-4bit | [HF Link](https://huggingface.co/TheBloke/Llama-2-7B-Chat-AWQ) |
-| llama2 | 7b-chat-fp16 | [HF Link](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) |
+| llama2 | 13b-chat-fp16-0b04 | [HF Link](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) |
+| llama2 | 70b-chat-fp16-4512 | [HF Link](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) |
+| llama2 | 7b-chat-awq-4bit-dcbf | [HF Link](https://huggingface.co/TheBloke/Llama-2-7B-Chat-AWQ) |
+| llama2 | 7b-chat-fp16-d960 | [HF Link](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) |
 
 ---
+
+
+###  <a id="mixtral"></a>
+
+| Model | Version | Huggingface Link |
+| --- | --- | --- |
+| mixtral | 8x7b-instruct-v0.1-awq-4bit-32eb | [HF Link](https://huggingface.co/casperhansen/mixtral-instruct-awq) |
+| mixtral | 8x7b-instruct-v0.1-fp16-d01a | [HF Link](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) |
+
+---
+