4 repos
apple/ml-cross-entropy
No description
617
0 commits
WooSunghyeon/dropbp
The official code for Dropping Backward Propagation (DropBP)
32
21 commits
suu990901/LLaMA-MiLe-Loss
Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
69
23 commits
awslabs/slapo
A schedule language for large model training
153
394 commits