Can't load the model using AutoModelForCausalLM

Models
1

Hi,

I have tried to load the llama-vision using AutoModelForCausalLM.from_pretrained, I am getting the following error.

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 This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command pip install --upgrade transformers. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command pip install git+https://github.com/huggingface/transformers.git

Any thought?
Thank you

1 Like
2

I think it’s as the error message says…
If the error persists after upgrading, there might be another cause, but upgrading comes first.

pip install -U transformers
3

I upgraded the Transformers package, yet the issue remains.

1 Like
4

Hmm, would the same situation occur if you used MllamaForConditionalGeneration or MllamaForCausalLM instead of AutoModelForCausalLM?