squall/flash-attention
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
ce26d3d73d
flash-attention/training/configs/experiment
History
Tri Dao 71befc19e1 [Loss] Use flash_attn.losses.cross_entropy.CrossEntropyLoss
2022-12-31 22:43:28 -08:00
..
owt [Loss] Use flash_attn.losses.cross_entropy.CrossEntropyLoss 2022-12-31 22:43:28 -08:00
pile [Loss] Use flash_attn.losses.cross_entropy.CrossEntropyLoss 2022-12-31 22:43:28 -08:00