You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+14Lines changed: 14 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -265,6 +265,20 @@ The [Hugging Face](https://huggingface.co) platform hosts a [number of LLMs](htt
265
265
266
266
You can either manually download the GGUF file or directly use any `llama.cpp`-compatible models from Hugging Face by using this CLI argument: `-hf <user>/<model>[:quant]`
267
267
268
+
llama.cpp also supports downloading and running models from [ModelScope](https://www.modelscope.cn/home), just add an env variable: `LLAMACPP_USE_MODELSCOPE=True` to your command with the same arguments(like `-hf <user>/<model>[:quant]`).
Pay attention to change the model repo to the **existing repo** of ModelScope. If you want to use a private repo, please make sure you have the rights of the repo and run with the `--hf_token` argument:
> You can change the endpoint of ModelScope by using `MODELSCOPE_DOMAIN=xxx`(like MODELSCOPE_DOMAIN=www.modelscope.ai).
281
+
268
282
After downloading a model, use the CLI tools to run it locally - see below.
269
283
270
284
`llama.cpp` requires the model to be stored in the [GGUF](https://github.com/ggml-org/ggml/blob/master/docs/gguf.md) file format. Models in other data formats can be converted to GGUF using the `convert_*.py` Python scripts in this repo.
0 commit comments