CoolFace
Modelpublic

idealab-cs2/reappraisal-4b-grpo-committee

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
1likes24downloads
10 commits on main
8e082a92mo ago

drop links to deleted near-duplicate HF repos

ruggsea
c60615b2mo ago

model card: exact cluster CIs (0.872 / CI-low 0.781; R1 h2h 0.673)

ruggsea
baa04182mo ago

Trim Evaluation to card-appropriate length; keep honest facts, cut the stats lecture

ruggsea
78d972f2mo ago

Correct R1 overclaims: retract iid CI-low vs R1 reference-rate; state honest vignette-cluster CI-low and OOD parity/loss vs R1 (R1-OOD program closed negative)

ruggsea
0351afe2mo ago

Trim caveats to card-appropriate length

ruggsea
a800f972mo ago

Card honesty pass: qualify judge calibration regime, note CI independence assumption + specialist framing, mark OOD gap as not significant

ruggsea
a8900a33mo ago

Match house writing style: remove non-native em dashes / flourishes

ruggsea
e6c05873mo ago

Update card: n=720 confirmed (0.872 CI-low 0.846) + direct-R1 head-to-head 0.671 + OOD 0.58 vs 0.52

ruggsea
5b621303mo ago

Upload folder using huggingface_hub

ruggsea
e0d1ee33mo ago

initial commit

ruggsea