SIGN IN SIGN UP

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

0 0 0 Python

:rotating_light: [`Clip`] Fix masking and enable flash attention on all model types (#41750)

* fix

* make kwargs fully passed and adjust with outputs xxx

* propogate metaclip 2

* propogate mlcd and fix test

* style

* fix repo consistency, need to add ignore rules as those are building blocks

* style

* oops

* fix mlcd
A
Anton Vlasjuk committed
7a833d1ccd41673030c85107f65f454c0c3222f5
Parent: 8bde822
Committed by GitHub <noreply@github.com> on 10/24/2025, 6:44:10 PM