SIGN IN SIGN UP

๐Ÿค— 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

[Model] Add PaddleOCR-VL Model Support (#42178)

* init

* refactor

* update

* update

* fix unresolved problems

* fix how position_ids work with flash_attn_2

* add tests and fix code

* add model_doc

* update model_doc

* fix ci

* update docstring

* add tests

* update

* add **kwargs

* update

* update

* update

* reduce max_position_embeddings in tests

* update
Z
zhang-prog committed
8c84144bfc7dd0c9c5e336a6d89c9dcee2efc2a8
Parent: 78b2992
Committed by GitHub <[email protected]> on 12/11/2025, 2:27:04 PM