monte-inc/tau2-banking-eval-results download history
monte-inc/tau2-banking-eval-results is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 43 times (6 in the last 7 days), and 193 times in total. It ranks #207,805 among datasets by monthly downloads.
tau2-bench Banking Eval Results (SFT) Full per-run eval results (results.json with transcripts) for SFT runs evaluated on tau2-bench's banking_knowledge domain. Each folder is one eval run. SFT'd Qwen / Gemma models from monte-inc are evaluated against this dataset's standard config and t
Open monte-inc/tau2-banking-eval-results on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.