Commit History
-
替换权重:S0B/S1B 底座重跑 SFT->CPO->GRPO(3000 prompt),recipe 修复 GRPO_LR 发散
Verified signature1eb5314 -
Upload README.md with huggingface_hub
Verified signature0e76354
-
Add files using upload-large-folder tool
Verified signature03d337a -
code + tokenizer + model card
Verified signaturea4251f4 -
initial commit
Verified signature756396c