search

microsoft / JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
MIT License
23.54k stars 1.96k forks source link

models_server can't work #108

Open dydwgmcnl4241 opened 1 year ago

dydwgmcnl4241 commented 1 year ago

Traceback (most recent call last): File "/Users/wilson/miniforge3/envs/jarvis/lib/python3.8/site-packages/transformers/modeling_utils.py", line 415, in load_state_dict return torch.load(checkpoint_file, map_location="cpu") File "/Users/wilson/miniforge3/envs/jarvis/lib/python3.8/site-packages/torch/serialization.py", line 815, in load return _legacy_load(opened_file, map_location, pickle_module, pickle_load_args) File "/Users/wilson/miniforge3/envs/jarvis/lib/python3.8/site-packages/torch/serialization.py", line 1033, in _legacy_load magic_number = pickle_module.load(f, pickle_load_args) _pickle.UnpicklingError: invalid load key, 'v'.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "models_server.py", line 343, in pipes = load_pipes(local_deployment) File "models_server.py", line 88, in load_pipes "model": VisionEncoderDecoderModel.from_pretrained(f"{local_fold}/nlpconnect/vit-gpt2-image-captioning"), File "/Users/wilson/miniforge3/envs/jarvis/lib/python3.8/site-packages/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py", line 363, in from_pretrained return super().from_pretrained(pretrained_model_name_or_path, *model_args, **kwargs) File "/Users/wilson/miniforge3/envs/jarvis/lib/python3.8/site-packages/transformers/modeling_utils.py", line 2477, in from_pretrained state_dict = load_state_dict(resolved_archive_file) File "/Users/wilson/miniforge3/envs/jarvis/lib/python3.8/site-packages/transformers/modeling_utils.py", line 420, in load_state_dict raise OSError( OSError: You seem to have cloned a repository without having git-lfs installed. Please install git-lfs and run git lfs install followed by git lfs pull in the folder you cloned.

avatarneil commented 1 year ago

Have you tried installing git-lfs, running git lfs install, and then running the server/models/download.sh script to fetch the models?

If you're looking for an easy-setup path, I'd recommend going with the HuggingFace Space runtime environment https://huggingface.co/spaces/microsoft/HuggingGPT