transformers
34678db4 - Fix Seq2seqTrainer decoder attention mask (#26841)

Commit

3 years ago

Fix Seq2seqTrainer decoder attention mask (#26841) Don't drop decoder_input_ids without also dropping decoder_attention_mask

References

#26841 - Fix Seq2seqTrainer decoder attention mask

#29969 - [SigLIP] Add fast tokenizer

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

#62 - Add initial DEIMv2 model implementation

#65 - Fix RTDetrV2 sine position embedding ordering

#71 - Use Mask2Former ignore_value in mask matching and losses

#45110 - Add SAM 3.1

Author

Rocketknight1

Rocketknight1

Parents

Loading