Skip to content

feat(training): train with verl through an AgentEnv agent loop - #422

Open
earakely-scale wants to merge 12 commits into
mainfrom
feat/verl-agent-loop
Open

earakely-scale wants to merge 12 commits into
mainfrom
feat/verl-agent-loop

fix(training): the verl writer counts prompts with verl's chat templa…

210888f
Select commit
Loading
Failed to load commit list.