reasoning-cues/rollouts-smollm3-rl download history

reasoning-cues/rollouts-smollm3-rl is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 194 times (18 in the last 7 days), and 194 times in total. It ranks #69,195 among datasets by monthly downloads.

rollouts-smollm3-rl — evaluation rollouts (boxed prompt) Model: reasoning-cues/smollm3-rl @ 97bda61 — a GRPO LoRA adapter (r=64, alpha=128, all attention and MLP projections) on HuggingFaceTB/SmolLM3-3B-Base @ d78a42f, merged with peft merge_and_unload (bf16) and served with the base

Open reasoning-cues/rollouts-smollm3-rl on Hugging Face

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