Commit History

Author SHA1 Message Date
  Tri Dao 71befc19e1 [Loss] Use flash_attn.losses.cross_entropy.CrossEntropyLoss 1 year ago
  Tri Dao dff68c2b22 Add smoothing for CrossEntropyParallel, rename to CrossEntropyLoss 2 years ago
  Tri Dao 0bf5e50038 Release training code 2 years ago