Khai Mai c5c69096b3 Exclude the load balancing loss of padding tokens in Mixtral-8x7B (#28517) ... * fix the function load_balancing_loss_func in Mixtral_Moe to include attention_mask * format code using black and ruff * skip computing mask if attention_mask=None * add tests for load balancing loss Mixtral-Moe * fix assert loss is different in mixtral_test * fix pad_leng * use assertNotAlmostEqual and print to debug * remove print for debug * minor updates * reduce rtol and atol		2024-01-24 10:12:14 +01:00
..
__init__.py
test_modeling_mixtral.py	Exclude the load balancing loss of padding tokens in Mixtral-8x7B (#28517)	2024-01-24 10:12:14 +01:00