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

[GLM-OCR] GLM-OCR Support (#43391)

* init

* update missing MTP

* update

* update

* update for headdim changed

* rename

* update for test

* rename for test

* format

* Update configuration_glm_ocr.py

* update init

* formate

* update config

* update for doc

* Update modular_glm_ocr.py

* update for map

* for test

* update for testing and comment

* Update test_modeling_glm_ocr.py

* rename GLM-V

* added after relase

* Update modeling_glm_ocr.py

* remove asset for ALL GLM-V model

* update vision model output to a `ModelOutput` and fix compile test

* run fix repo

---------

Co-authored-by: raushan <[email protected]>
Y
Yuxuan Zhang committed
4854dbf9da4086731256496cf4a8e4ea45d4d54e
Parent: a1f63d5
Committed by GitHub <[email protected]> on 1/27/2026, 12:22:33 PM