Raushan Turganbay 0a52bd2403 [fix] sliding window attention mask (#38045) ...

* fix sliding attn

* make style

* Update tests/test_modeling_common.py

Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>

* no a second throught, should default to `True` fo BC

---------

Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>

2025-05-20 09:32:19 +00:00

224 KiB

Executable File

Raw Blame History

View Raw