hour1
/

collabllm

Model card Files Files and versions

collabllm / examples /reinforce_plus_plus_trainer

4.09 kB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

hour1's picture

Upload folder using huggingface_hub

9114cf2 verified 4 months ago

run_qwen2-7b_math_rf.sh

2.04 kB
Upload folder using huggingface_hub 4 months ago
run_qwen2-7b_math_rf_baseline.sh

2.05 kB
Upload folder using huggingface_hub 4 months ago