Add GRPO/ Online DPO support for quantitative models when use vllm as infer backbone.#3133
Closed
maoulee wants to merge 0 commit intohuggingface:mainfrom
Closed
Add GRPO/ Online DPO support for quantitative models when use vllm as infer backbone.#3133maoulee wants to merge 0 commit intohuggingface:mainfrom
maoulee wants to merge 0 commit intohuggingface:mainfrom
Commits
No commits history
There isn't any commit history to show here.