Use fastchat with download vicuna cpp model

[rohezal]

Vicuna was build and worked as main.cpp by mself. But after this, I installed fastchat and it can't use the vicuna.cpp model file. Is it possible to fix this?

(fastchat) rohezal@box:/media/ai/fastchat/FastChat$ python3 -m fastchat.serve.cli --model-path /media/ai/llama/llama.cpp/models/ --device cpu
│                                                                                                  │
│ /home/rohezal/anaconda3/envs/fastchat/lib/python3.10/site-packages/transformers/utils/hub.py:380 │
│ in cached_file                                                                                   │
│                                                                                                  │
│    377 │   │   resolved_file = os.path.join(os.path.join(path_or_repo_id, subfolder), filename)  │
│    378 │   │   if not os.path.isfile(resolved_file):                                             │
│    379 │   │   │   if _raise_exceptions_for_missing_entries:                                     │
│ ❱  380 │   │   │   │   raise EnvironmentError(                                                   │
│    381 │   │   │   │   │   f"{path_or_repo_id} does not appear to have a file named {full_filen  │
│    382 │   │   │   │   │   f"'https://huggingface.co/{path_or_repo_id}/{revision}' for availabl  │
│    383 │   │   │   │   )                                                                         │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
OSError: /media/ai/llama/llama.cpp/models/ does not appear to have a file named config.json. Checkout 'https://huggingface.co//media//ai/llama/llama.cpp/models//None' for 
available files.

(fastchat) rohezal@box:/media/ai/fastchat/FastChat$ python3 -m fastchat.serve.cli --model-path /media/ai/llama/llama.cpp/models/ggml-vic13b-uncensored-q5_1.bin --device cpu

│                                                                                                  │
│ /home/rohezal/anaconda3/envs/fastchat/lib/python3.10/site-packages/huggingface_hub/utils/_valida │
│ tors.py:160 in validate_repo_id                                                                  │
│                                                                                                  │
│   157 │   │   raise HFValidationError(f"Repo id must be a string, not {type(repo_id)}: '{repo_   │
│   158 │                                                                                          │
│   159 │   if repo_id.count("/") > 1:                                                             │
│ ❱ 160 │   │   raise HFValidationError(                                                           │
│   161 │   │   │   "Repo id must be in the form 'repo_name' or 'namespace/repo_name':"            │
│   162 │   │   │   f" '{repo_id}'. Use `repo_type` argument if needed."                           │
│   163 │   │   )                                                                                  │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/media//ai/llama/llama.cpp/models/ggml-vic13b-uncensored-q5_1.bin'. Use `repo_type` argument if needed.

[kingwap99]

faced the same issue

[rohezal]

I am now just using ooga booga:

https://github.com/oobabooga/text-generation-webui