transformers
0d0d7769 - Allow trainer to return eval. loss for CLIP-like models (#20214)

Commit

3 years ago

Allow trainer to return eval. loss for CLIP-like models (#20214) * Allow trainer to return loss for CLIP-like models * Apply suggestions * update * update * update Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

References

#19449 - [WIP] Fix weights initialization of several vision models

#20214 - Allow trainer to return eval. loss for CLIP-like models

#27720 - Add common processor tests

#29969 - [SigLIP] Add fast tokenizer

#32831 - [Docs] Update resources

#33111 - [Backbone] Remove out_features everywhere

#33174 - [Zero-shot image classification pipeline] Remove tokenizer_kwargs

#39821 - Support MetaCLIP 2

#59 - Fix attention mask handling in EoMT-DINOv3 converter

#62 - Add initial DEIMv2 model implementation

Author

ydshieh

Parents

822ae69c

transformers 0d0d7769 - Allow trainer to return eval. loss for CLIP-like models (#20214)

transformers
0d0d7769 - Allow trainer to return eval. loss for CLIP-like models (#20214)