Hugging Face's logo

devtaji
/
OpenThinker-Agent-repro-RL

Safetensors
qwen3
Model card Files
xet
 Community
OpenThinker-Agent-repro-RL
32.8 GB
  • 1 contributor
 History: 23 commits
devtaji's picture
devtaji
RL GRPO step 55 (lr=1e-5, 728 tasks, Qwen3-8B)
b695f49 verified