gililior/wild-if-eval-predictions download history

gililior/wild-if-eval-predictions is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 164 times (22 in the last 7 days), and 394 times in total. It ranks #79,170 among datasets by monthly downloads.

WildIFEval - Model Predictions & Judge Scores Companion artifact dataset for WildIFEval: Instruction Following in the Wild. It holds the raw model responses and LLM-as-a-judge scores used to produce the paper's results, so they can be reproduced without re-running inference. Benchmark da

Open gililior/wild-if-eval-predictions on Hugging Face

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