ToolACE 8B ToolACE 8B is a finetuned model of LLaMA 3.1 8B Instruct with our dataset ToolACE tailored for tool usage. ToolACE 8B achieves state of the art performance on the Berkeley Function Calling Leaderboard(BFCL), rivaling the latest GPT 4 models. ToolACE is an automatic agentic pipeline designed to generate A ccurate, C omplex, and div E rse tool learning data. ToolACE leverages a novel self evolution synthesis process to curate a comprehensive API pool of 26,507 diverse APIs. Dialogs are further generated through the interplay among multiple agents, guided by a formalized thinking process. To ensure data accuracy, we implement a dual layer verification system combining rule based and model based checks. More details can be found in our paper on ICLR2025: ToolACE: Winning the Points of LLM Function Calling Here are the winning scores of ToolACE in BFCL v3). Usage Here we provide a code snippet with apply chat template to show you how to load the tokenizer and model and how to generate function calling with given functions. Then you should be able to see the following output functional calls: Citation If you think ToolACE is useful in your work, please cite our paper:
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy