stindardlogic/tool-use-dpo-100k download history
stindardlogic/tool-use-dpo-100k is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 42 times (7 in the last 7 days), and 132 times in total. It ranks #211,076 among datasets by monthly downloads.
Tool Use DPO (100K) 100,000 DPO preference pairs for training models to make correct tool use decisions. Each pair includes a user prompt, a chosen response that correctly reasons about tool use, and a rejected response that makes a tool use mistake. Covers 6 decision categories and 2