llm的rlhf强化学习微调 #81

Open

opened

on Dec 27, 2024

请问telechat支持rlhf训练吗，还有就是有训练时强有力的baseline的超参数组合吗

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests