EPFL-LARA/lean-world-model-reasoning-sft download history
EPFL-LARA/lean-world-model-reasoning-sft is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 202 times (18 in the last 7 days), and 286 times in total. It ranks #89,151 among datasets by monthly downloads.
Informal-reasoning SFT corpus The additional reasoning data for WM8 + reasoning and S8 + reasoning in Formal Theorem Proving with Lean World Models. Kimi-K2.7-Code supplies an informal plan for each proof attempt, including reasoning updates for repair histories. Split Rows Cont
Models trained on lean-world-model-reasoning-sft
4 models list it as training data.
- EPFL-LARA/lean-world-model-qwen3-8b-reasoning-grpo 958 downloads in 30 days
- EPFL-LARA/lean-standard-prover-qwen3-8b-reasoning-grpo 895 downloads in 30 days
- mradermacher/lean-standard-prover-qwen3-8b-reasoning-grpo-GGUF 826 downloads in 30 days
- mradermacher/lean-world-model-qwen3-8b-reasoning-grpo-GGUF 386 downloads in 30 days
Open EPFL-LARA/lean-world-model-reasoning-sft on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.