ToolACE-8B is an 8 billion parameter instruction-tuned causal language model developed by Team-ACE, based on LLaMA-3.1-8B-Instruct. This model is specifically fine-tuned for advanced tool usage and function calling, achieving state-of-the-art performance on the Berkeley Function-Calling Leaderboard. It excels at accurately interpreting user queries to generate complex and diverse tool-learning data, rivaling leading proprietary models.
No reviews yet. Be the first to review!