baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Fix server doc arguments (#892)

Browse source
This commit is contained in:
Kevin Jung 2023-11-08 23:53:00 -05:00 committed by GitHub
parent 80f4162bf4
commit fb1f956a27
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/server.md
View file

@ -45,7 +45,7 @@ You'll first need to download one of the available function calling models in GG
Then when you run the server you'll need to also specify the `functionary-7b-v1` chat_format
```bash
python3 -m llama_cpp.server --model <model_path> --chat-format functionary
python3 -m llama_cpp.server --model <model_path> --chat_format functionary
```
### Multimodal Models
@ -61,7 +61,7 @@ You'll first need to download one of the available multi-modal models in GGUF fo
Then when you run the server you'll need to also specify the path to the clip model used for image embedding and the `llava-1-5` chat_format
```bash
python3 -m llama_cpp.server --model <model_path> --clip-model-path <clip_model_path> --chat-format llava-1-5
python3 -m llama_cpp.server --model <model_path> --clip_model_path <clip_model_path> --chat_format llava-1-5
```
Then you can just use the OpenAI API as normal