reasoning-cues/rollouts-qwen4b-rl download history

reasoning-cues/rollouts-qwen4b-rl is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 220 times (92 in the last 7 days), and 220 times in total. It ranks #62,554 among datasets by monthly downloads.

rollouts-qwen4b-rl — evaluation rollouts Model: amildravid4292/Qwen3-4B-Base-GRPO-MATH-ck300. Tokenizer used for answer positions: Qwen/Qwen3-4B-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-qwen4b-rl on Hugging Face

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