Using CogVLM - KeyError (MODEL_URLS) - Google Colab
Baggiorobertozoba opened this issue · comments
User
!python cli_demo_sat.py --from_pretrained /content/drive/MyDrive/MyProject/CogVLM/cogvlm-chat-v1.1/1/mp_rank_00_model_states.pt --fp16 --quant 4 --stream_chat
[2024-02-11 00:28:23,218] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Please build and install Nvidia apex package with option '--cuda_ext' according to https://github.com/NVIDIA/apex#from-source .
Traceback (most recent call last):
File "/content/CogVLM/basic_demo/cli_demo_sat.py", line 161, in
main()
File "/content/CogVLM/basic_demo/cli_demo_sat.py", line 36, in main
model, model_args = AutoModel.from_pretrained(
File "/usr/local/lib/python3.10/dist-packages/sat/model/base_model.py", line 337, in from_pretrained
return cls.from_pretrained_base(name, args=args, home_path=home_path, url=url, prefix=prefix, build_only=build_only, overwrite_args=overwrite_args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/sat/model/base_model.py", line 312, in from_pretrained_base
model_path = auto_create(name, path=home_path, url=url)
File "/usr/local/lib/python3.10/dist-packages/sat/resources/download.py", line 53, in auto_create
url = MODEL_URLS[name]
KeyError: '/content/drive/MyDrive/MyProject/CogVLM/cogvlm-chat-v1.1/1/mp_rank_00_model_states.pt'
FYI: