google

/

gemma-7b-it

like 1.1k

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="google/gemma-7b-it")

Is resulting in a KeyError on colab:

---------------------------------------------------------------------------
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)
   1116             try:
-> 1117                 config_class = CONFIG_MAPPING[config_dict["model_type"]]
   1118             except KeyError:

3 frames
KeyError: 'gemma'

During handling of the above exception, another exception occurred:

ValueError                                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)
   1117                 config_class = CONFIG_MAPPING[config_dict["model_type"]]
   1118             except KeyError:
-> 1119                 raise ValueError(
   1120                     f"The checkpoint you are trying to load has model type `{config_dict['model_type']}` "
   1121                     "but Transformers does not recognize this architecture. This could be because of an "

ValueError: The checkpoint you are trying to load has model type `gemma` 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 This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

Is there something obvious that I am missing?