kshitijthakkar/arena-all8-v32-field-reward download history
kshitijthakkar/arena-all8-v32-field-reward is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 141 times (9 in the last 7 days), and 141 times in total. It ranks #116,260 among datasets by monthly downloads.
Eight-domain MetaHarness OpenEnv bank with field-level partial credit (v32) An OpenEnv environment for the OpenEnv Arena: 50 deterministic, synthetic, file-based tasks across the eight Arena domains. The model works with three tools, list, read (path: "*" reads all task evidence) and
Open kshitijthakkar/arena-all8-v32-field-reward on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.