transformers
482cb28a - Fix `tie_word_embeddings` handling for GGUF models (#35085)

Commit

1 year ago

Fix `tie_word_embeddings` handling for GGUF models (#35085) * fix tie_word_embeddings Signed-off-by: Isotr0py <2037008807@qq.com> * fix Signed-off-by: Isotr0py <2037008807@qq.com> --------- Signed-off-by: Isotr0py <2037008807@qq.com>

References

#35085 - Fix `tie_word_embeddings` handling for GGUF models

#39821 - Support MetaCLIP 2

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

#62 - Add initial DEIMv2 model implementation

#65 - Fix RTDetrV2 sine position embedding ordering

#43710 - [Docs] Add docs for GLM-OCR and fix EomT-DINOv3

Author

Isotr0py

Parents

35447054

transformers 482cb28a - Fix `tie_word_embeddings` handling for GGUF models (#35085)

transformers
482cb28a - Fix `tie_word_embeddings` handling for GGUF models (#35085)