meta-llama

/

Llama-3.2-11B-Vision

like 286

I get an error when running this code sample from Transformers library:

# Load model directly
from transformers import AutoProcessor, AutoModelForPreTraining

processor = AutoProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision")
model = AutoModelForPreTraining.from_pretrained("meta-llama/Llama-3.2-11B-Vision")

Error:

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/transformers/models/auto/configuration_auto.py in from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
    992             try:
--> 993                 config_class = CONFIG_MAPPING[config_dict["model_type"]]
    994             except KeyError:

3 frames
/usr/local/lib/python3.10/dist-packages/transformers/models/auto/configuration_auto.py in __getitem__(self, key)
    694         if key not in self._mapping:
--> 695             raise KeyError(key)
    696         value = self._mapping[key]

KeyError: 'mllama'

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
<ipython-input-18-bc2ee643b38e> in <cell line: 2>()
      1 # Load model
----> 2 processor = AutoProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision")
      3 model = AutoModelForPreTraining.from_pretrained("meta-llama/Llama-3.2-11B-Vision")

/usr/local/lib/python3.10/dist-packages/transformers/models/auto/processing_auto.py in from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
    290             # Otherwise, load config, if it can be loaded.
    291             if not isinstance(config, PretrainedConfig):
--> 292                 config = AutoConfig.from_pretrained(
    293                     pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
    294                 )

/usr/local/lib/python3.10/dist-packages/transformers/models/auto/configuration_auto.py in from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
    993                 config_class = CONFIG_MAPPING[config_dict["model_type"]]
    994             except KeyError:
--> 995                 raise ValueError(
    996                     f"The checkpoint you are trying to load has model type `{config_dict['model_type']}` "
    997                     "but Transformers does not recognize this architecture. This could be because of an "

ValueError: The checkpoint you are trying to load has model type `mllama` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.