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.

158577 0 0 Python

Fixes configuration default values (#43592)

* fixes it finally I hope for all models!

* tie word embeddings!

* vision LLMs

* Apply repo consistency fixes

* Apply repo consistency fixes

* revert VLMs

* unpleasant bug

* fix repo

* skip it

* llava mismatch

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
R
Raushan Turganbay committed
562106fe4aff6141b6651f3b6c6220de7c6e96a6
Parent: ee94767
Committed by GitHub <[email protected]> on 1/30/2026, 11:37:25 AM