hotdogs/thinkingcap-sft-qwen38-27b download history

hotdogs/thinkingcap-sft-qwen38-27b is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 62 times (21 in the last 7 days), and 266 times in total. It ranks #220,560 among datasets by monthly downloads.

ThinkingCap SFT + DPO — Qwen3.8-27B (on-policy, oracle-verified) Efficient-reasoning dataset built the same way as BottleCap's ThinkingCap-Qwen3.6-27B, but collected on-policy from the live abliterated Qwen3.8-27B-MTP and verified against independently-recomputed oracles (correctness

Models trained on thinkingcap-sft-qwen38-27b

4 models list it as training data.

Open hotdogs/thinkingcap-sft-qwen38-27b on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.