PaulR11/eval-suite-v2 download history

PaulR11/eval-suite-v2 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 128 times (83 in the last 7 days), and 11,620 times in total. It ranks #95,127 among datasets by monthly downloads.

Evaluation Suite V2 — Comprehensive Run (48 models, 150+ plots) Part of the data release for "Training Alignment Auditors via Reinforcement Learning" (ICLR 2026). The second-wave comprehensive evaluation run covering 48 auditor configurations, used to generate per-epoch scaling figures an

Open PaulR11/eval-suite-v2 on Hugging Face

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