feat(mini_swe_env): add SWE-Gym async GRPO environment with Pi interception and HF Space deployment#695
Open
rycerzes wants to merge 83 commits into
Open
feat(mini_swe_env): add SWE-Gym async GRPO environment with Pi interception and HF Space deployment#695rycerzes wants to merge 83 commits into
rycerzes wants to merge 83 commits into