legendarydragontamer/turboskillslug-groundedness-eval download history

legendarydragontamer/turboskillslug-groundedness-eval is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 15 times (5 in the last 7 days), and 76 times in total. It ranks #450,867 among datasets by monthly downloads.

TurboSkillSlug Groundedness Eval Does a fine-tuned 1.5B extraction model hallucinate more than the Qwen-7B it replaced? This dataset is the measurement: three systems, 25 held-out transcripts, two groundedness metrics, with the raw generations included so anyone can re-score with thei

Spaces using turboskillslug-groundedness-eval

Open legendarydragontamer/turboskillslug-groundedness-eval on Hugging Face

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