-
Notifications
You must be signed in to change notification settings - Fork 7
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat(llamacpp_chat): support larger models
- Loading branch information
agent
authored and
agent
committed
Oct 8, 2024
1 parent
792fcd1
commit d752e70
Showing
3 changed files
with
113 additions
and
24 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,11 +1,35 @@ | ||
project: llamacpp-chat | ||
service_config: | ||
name: phi3 | ||
traffic: | ||
timeout: 300 | ||
resources: | ||
memory: 3Gi | ||
engine_config: | ||
model: microsoft/Phi-3-mini-4k-instruct-gguf | ||
max_model_len: 2048 | ||
chat_template: phi-3 | ||
project: llamacpp-chat | ||
engine_config: | ||
max_model_len: 2048 | ||
additional_files: | ||
- qwen2.5-32b-instruct-fp16-00001-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00002-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00003-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00004-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00005-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00006-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00007-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00008-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00009-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00010-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00011-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00012-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00013-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00014-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00015-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00016-of-00017.gguf | ||
- qwen2.5-32b-instruct-fp16-00017-of-00017.gguf | ||
filename: qwen2.5-32b-instruct-fp16-00001-of-00017.gguf | ||
repo_id: Qwen/Qwen2.5-32B-Instruct-GGUF | ||
extra_labels: | ||
model_name: Qwen/Qwen2.5-72B-Instruct-GGUF | ||
openllm_alias: 32b-ggml-fp16 | ||
service_config: | ||
name: qwen2.5 | ||
resources: | ||
memory: 60Gi | ||
traffic: | ||
timeout: 300 | ||
extra_envs: | ||
- name: CMAKE_ARGS | ||
value: "-DGGML_METAL=on" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters