Commit History
3 days ago
-
Model card: update GRPO eval with reasoning warm-up results
Verified signaturede36c2d -
Upload models/grpo_qwen06_merged
Verified signature5c0931f -
Upload models/grpo_qwen06
Verified signature8eed597 -
Upload models/reasoning_warmup_qwen06_merged
Verified signature916382a -
Upload models/reasoning_warmup_qwen06
Verified signature6ed71d2
4 days ago
-
Fix opening think tag in README
Verified signature135e2dc -
Add model card / README for the checkpoint repository
Verified signature0503640 -
Upload folder using huggingface_hub
Verified signature0f2aeea -
Upload full pipeline: CPT/SFT/DPO/warmup/GRPO
Verified signature08c0e0b -
initial commit
Verified signature1dcb7ff