Jordine/rl-natural-self-calibration download history

Jordine/rl-natural-self-calibration is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 387 times (56 in the last 7 days), and 1,168 times in total. It ranks #40,356 among datasets by monthly downloads.

RL & Natural Self-Calibration Does RL induce a model's self-knowledge of its own capacity/size? Experiments on Qwen2.5 (0.5–14B) and OLMo-3-7B (base / SFT / RL-Zero{Math,Code,General} / Think / Instruct). Scripts, probe outputs, and findings. (Research scaffold — read FINDINGS_*.md in

Open Jordine/rl-natural-self-calibration on Hugging Face

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