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

Fix docs multi-modal docs

Browse source
This commit is contained in:
Andrei Betlen 2023-11-07 22:52:08 -05:00
parent aab74f0b2b
commit 3660230faa
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

@ -44,10 +44,10 @@ You'll first need to download one of the available multi-modal models in GGUF fo
- [llava1.5 7b](https://huggingface.co/mys/ggml_llava-v1.5-7b) - [llava1.5 7b](https://huggingface.co/mys/ggml_llava-v1.5-7b)
- [llava1.5 13b](https://huggingface.co/mys/ggml_llava-v1.5-13b) - [llava1.5 13b](https://huggingface.co/mys/ggml_llava-v1.5-13b)
Then when you run the server you'll need to also specify the path to the clip model used for image embedding 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 ```bash
python3 -m llama_cpp.server --model <model_path> --clip-model-path <clip_model_path> 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 Then you can just use the OpenAI API as normal