altrastorique / automodelforcausallm Goto Github PK

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map='auto',
    quantization_config=nf4_config,
    use_cache=False,
    attn_implementation="flash_attention_2"

)

ImportError                               Traceback (most recent call last)

Cell In[26], line 1
----> 1 model = AutoModelForCausalLM.from_pretrained(
      2     model_id,
      3     device_map='auto',
      4     quantization_config=nf4_config,
      5     use_cache=False,
      6     attn_implementation="flash_attention_2"
      7 
      8 )

File ~\anacondaNewV\envs\tensorflow\lib\site-packages\transformers\models\auto\auto_factory.py:563, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
    561 elif type(config) in cls._model_mapping.keys():
    562     model_class = _get_model_class(config, cls._model_mapping)
--> 563     return model_class.from_pretrained(
    564         pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
    565     )
    566 raise ValueError(
    567     f"Unrecognized configuration class {config.__class__} for this kind of AutoModel: {cls.__name__}.\n"
    568     f"Model type should be one of {', '.join(c.__name__ for c in cls._model_mapping.keys())}."
    569 )

File ~\anacondaNewV\envs\tensorflow\lib\site-packages\transformers\modeling_utils.py:3049, 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)
   3046     hf_quantizer = None
   3048 if hf_quantizer is not None:
-> 3049     hf_quantizer.validate_environment(
   3050         torch_dtype=torch_dtype, from_tf=from_tf, from_flax=from_flax, device_map=device_map
   3051     )
   3052     torch_dtype = hf_quantizer.update_torch_dtype(torch_dtype)
   3053     device_map = hf_quantizer.update_device_map(device_map)

File ~\anacondaNewV\envs\tensorflow\lib\site-packages\transformers\quantizers\quantizer_bnb_4bit.py:62, in Bnb4BitHfQuantizer.validate_environment(self, *args, **kwargs)
     60 def validate_environment(self, *args, **kwargs):
     61     if not (is_accelerate_available() and is_bitsandbytes_available()):
---> 62         raise ImportError(
     63             "Using `bitsandbytes` 8-bit quantization requires Accelerate: `pip install accelerate` "
     64             "and the latest version of bitsandbytes: `pip install -i https://pypi.org/simple/ bitsandbytes`"
     65         )
     67     if kwargs.get("from_tf", False) or kwargs.get("from_flax", False):
     68         raise ValueError(
     69             "Converting into 4-bit or 8-bit weights from tf/flax weights is currently not supported, please make"
     70             " sure the weights are in PyTorch format."
     71         )

ImportError: Using `bitsandbytes` 8-bit quantization requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes: 'pip install -i https://pypi.org/simple/ bitsandbytes`

!pip install accelerate
!pip install -i https://pypi.org/simple/ bitsandbytes