transformers
e768616a - Fix load balancing loss func for mixtral (#28256)

Commit
2 years ago
Fix load balancing loss func for mixtral (#28256) * Correct the implementation of auxiliary loss of mixtrtal * correct the implementation of auxiliary loss of mixtrtal * Implement a simpler calculation method --------- Co-authored-by: zhangliangxu3 <zhangliangxu3@jd.com>
Author
Parents
Loading