Poedator a0779b9e19 Llama: fix custom 4D masks, v2 (#30348) ... * 4d mask fixes * Update custom 4D mask logic * test moved to mixin * extra tests 4d mask * upd 4d mask and StaticCache handling * added Mask4DTestHard to mistral tests * post-rebase fixes * test fixes for StaticCache * make fix-copies * upd 1 after #30476 * fix common tests * rm elif attention_mask.dim() == 4: * tests combined, fixed, mixtral supported * bigbird style chg reverted * rm if attention_mask.dim() == 2 * modeling_llama formatting chg --------- Co-authored-by: Joao Gante <joao@huggingface.co>		2024-05-13 13:46:06 +02:00
..
__init__.py	[Mistral] Mistral-7B-v0.1 support (#26447)	2023-09-27 18:30:46 +02:00
test_modeling_flax_mistral.py	Flax mistral (#26943)	2024-01-31 14:19:02 +01:00
test_modeling_mistral.py	Llama: fix custom 4D masks, v2 (#30348)	2024-05-13 13:46:06 +02:00