CoolFace
Modelpublic

johnbean393/qwen3.5-4b-reasoning-effort-grpo

sourceHugging Faceupdated 2mo agoView on Hugging Face
1likes
8 commits on main
e708ecf2mo ago

Hourly adapter snapshot at step 377

johnbean393
c4b2a302mo ago

Hourly adapter snapshot at step 298

johnbean393
9de38552mo ago

Hourly adapter snapshot at step 219

johnbean393
611bb5a2mo ago

Hourly adapter snapshot at step 139

johnbean393
ee75cf82mo ago

Hourly adapter snapshot at step 65 (recovered)

johnbean393
b204b642mo ago

Add frozen 512-problem SGLang natural-length calibration

johnbean393
16774912mo ago

Add frozen 512-problem SGLang natural-length calibration

johnbean393
ae2e9c52mo ago

initial commit

johnbean393