Raushan Turganbay 01ad9f4b49 Bart: new cache format (#35314) ... * bart compile * add mbart * some more models touched by fix-copies * more * more models * even more models * fix copies * fix tests * fix copies * fix * biogpt accepts position ids now (breaking?) * fix failing non-slow tests * fix some tests * should not be removed * small update * Update src/transformers/models/bart/modeling_bart.py Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com> * update for last `main` * fix copies * clone `update_causal_mask` from llama * tmp * fixup * why? how? * fix bart tests * dont skip test * address comments * fix tests * fix * fixup and delete the file --------- Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>		2025-05-16 13:26:54 +02:00
..
__init__.py	Add BioGPT (#20420)	2022-12-05 10:12:03 -05:00
test_modeling_biogpt.py	Bart: new cache format (#35314)	2025-05-16 13:26:54 +02:00
test_tokenization_biogpt.py	Use Python 3.9 syntax in tests (#37343)	2025-04-08 14:12:08 +02:00