如果只是想学大模型后训练包括dpo ppo grpo这些po算法的话，需要从0读起吗 #8

Open

opened

感觉现在大模型领域的rl算法和这些之前的rl算法相差甚远啊

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests