FineEnvs/fineproof-envs-train download history
FineEnvs/fineproof-envs-train is an other dataset on the Hugging Face Hub. In the last 30 days it was downloaded 916 times (794 in the last 7 days), and 916 times in total. It ranks #29,966 among datasets by monthly downloads.
FineProofEnvs: train (Harbor) Write an olympiad proof, graded against a marking scheme. 5,073 Harbor tasks from lm-provers/FineProofs-RL, the proof problems used to train QED-Nano, converted so every one runs as a standard Harbor task. The agent gets a problem and a sandbox with Pyth
Models trained on fineproof-envs-train
1 models list it as training data.
- FineEnvs/Qwen3.5-2B-FineProof-RL 71 downloads in 30 days
Open FineEnvs/fineproof-envs-train on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.