zswzswzsw
/

verl_subquestion

Model card Files Files and versions

verl_subquestion / examples /reinforce_plus_plus_trainer

4.37 kB

1 contributor

History: 1 commit

zswzswzsw's picture

Upload folder using huggingface_hub

66407c5 verified about 1 month ago

run_qwen2-7b_math_rf.sh

2.18 kB

Upload folder using huggingface_hub about 1 month ago
run_qwen2-7b_math_rf_baseline.sh

2.19 kB

Upload folder using huggingface_hub about 1 month ago