Errors loading the Mixtral-8x7B-Instruct-v0.1 model
I'm loading the model from huggingface and getting this error:
model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
 1 model = AutoModelForCausalLM.from_pretrained(model_id)
      2 model.save_pretrained(f"mistralai/model/{model_id}")
File ~/miniconda3/envs/ex/lib/python3.12/site-packages/transformers/models/auto/auto_factory.py:564, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
    562 elif type(config) in cls._model_mapping.keys():
    563     model_class = _get_model_class(config, cls._model_mapping)
--> 564     return model_class.from_pretrained(
    565         pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
    566     )
    567 raise ValueError(
    568     f"Unrecognized configuration class {config.class} for this kind of AutoModel: {cls.name}.\n"
    569     f"Model type should be one of {', '.join(c.name for c in cls._model_mapping.keys())}."
    570 )
File ~/miniconda3/envs/ex/lib/python3.12/site-packages/transformers/modeling_utils.py:3838, in PreTrainedModel.from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)
   3828     if dtype_orig is not None:
   3829         torch.set_default_dtype(dtype_orig)
   3831     (
   3832         model,
   3833         missing_keys,
   3834         unexpected_keys,
   3835         mismatched_keys,
...
--> 516     with safe_open(checkpoint_file, framework="pt") as f:
    517         metadata = f.metadata()
    518     if metadata.get("format") not in ["pt", "tf", "flax", "mlx"]:
OSError: No such device (os error 19)
I need help!!!
hey @fdzr you might find Impulse AI (https://www.impulselabs.ai/) useful. we make it super easy to fine-tune and deploy open source models. hopefully you find it helpful! i know not relevant to your problem above but might be easier to use us to fine tune and deploy
docs: https://docs.impulselabs.ai/introduction
python sdk: https://pypi.org/project/impulse-api-sdk-python/
