CoolFace
Modelpublic

CL-From-Nothing/rl_warmup_rlve_offline_20K-parquet_qwen3-1.7b_epoch_1_mask

sourceHugging Faceupdated 4mo agoView on Hugging Face
0likes24downloads
2 commits on main
02898c54mo ago

SFT-warmup Qwen3-1.7B on rlve_offline_20K (1 epoch, loss on all response tokens; from global_step_156)

SuhaoYu1020
75a3e1a4mo ago

initial commit

SuhaoYu1020