reasoning-cues/rollouts-qwen14b-rl download history

reasoning-cues/rollouts-qwen14b-rl is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 276 times (94 in the last 7 days), and 276 times in total. It ranks #52,426 among datasets by monthly downloads.

rollouts-qwen14b-rl — evaluation rollouts Model: GRPO ck300 merged from Qwen/Qwen3-14B-Base. Tokenizer used for answer positions: Qwen/Qwen3-14B-Base. Protocol: 32 rollouts per problem (two seeded batches of 16), temperature 0.6, top-p 0.95, budget 31,744 generated tokens, seed 202608

Open reasoning-cues/rollouts-qwen14b-rl on Hugging Face

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