Image-Text-to-Text
Transformers
Safetensors
English
idefics2
pretraining
multimodal
vision
Inference Endpoints
5 papers

Which version of transformers?

#2
by harpreetsahota - opened

Running the following, using transformers 4.39.3

from transformers import AutoProcessor, AutoModelForVision2Seq


processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics2-8b")
model = AutoModelForVision2Seq.from_pretrained("HuggingFaceM4/idefics2-8b")

Yields an error:

ValueError: The checkpoint you are trying to load has model type `idefics2` 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 This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

Which version of transformers should be used for this model?

HuggingFaceM4 org

Hi @harpreetsahota ,
Idefics2 was integrated into main 2 hours ago and is not in a pypi release yet. can you install transformer from source for now?

Cheers @VictorSanh - appreciate it!

harpreetsahota changed discussion status to closed
HuggingFaceM4 org

Sign up or log in to comment