CoolFace
Modelpublic

SelectiveDOPD/JustRL-Qwen3-1p7b-DirectOPD

sourceHugging Faceupdated 15d agoView on Hugging Face
0likes229downloads
Model Card

JustRL-Qwen3-1p7b-DirectOPD

Uploaded from justrl_qwen3_1p7b in the BiDirect-OPD experiments.

The main branch contains global_step_300. Available checkpoint branches:

  • —global_step_20
  • —global_step_40
  • —global_step_60
  • —global_step_80
  • —global_step_100
  • —global_step_120
  • —global_step_140
  • —global_step_160
  • —global_step_180
  • —global_step_200
  • —global_step_220
  • —global_step_240
  • —global_step_260
  • —global_step_280
  • —global_step_300