Hugging Face's logo

hf-internal-testing
/
tiny-random-clip

Transformers
PyTorch
clip
Model card Files
xet
 Community
4

V4.22.0 processor update

#2
by lewtun HF Staff - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+147315
-607
lewtun
 Hugging Face Internal Testing Organization org
•
edited Sep 8, 2022

This PR follows #1 and:

  • updates the CLIP model to be compatible with transformers v4.22. The previous version throws an error when trying to load the tokenizer (requires from_slow=True)
  • sets the image and crop size to the default value of 30 associated with the checkpoint this model was derived from

cc @ydshieh

V4.22.0 updateeea3ef08
lewtun changed pull request title from V4.22.0 update to V4.22.0 processor update
ydshieh
 Hugging Face Internal Testing Organization org

The change in tokenizer_config.jsonseems strange to me. It contains crop_size, size, processor_class. I guess it is somehow mixing the fields from preprocessor_config.json?
lewtun
 Hugging Face Internal Testing Organization org

I generated tokenizer._config.json by using CLIPProcessor.push_to_hub() - presumably these fields are added automatically?
Rocketknight1
 Hugging Face Internal Testing Organization org

Quick ping on this PR, I encountered this issue while running some TF tests. Is it okay to merge?
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment