CoolFace
Modelpublic

SelectiveDOPD/QuestA-Distilled-DeepSeek-7b-Selective-Top10pct

sourceHugging Faceupdated 13d agoView on Hugging Face
0likes173downloads
Model Card

QuestA-Distilled-DeepSeek-7b-Selective-Top10pct

Uploaded from questa_deepseek_r1_7b_JSD_rel_90_100 in the BiDirect-OPD experiments.

The main branch contains global_step_300. Available earlier 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