llm-agents/tora-7b-v1.0
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Oct 8, 2023License:llama2Architecture:Transformer0.0K Open Weights Cold

ToRA-7B-v1.0 is a 7 billion parameter Tool-integrated Reasoning Agent developed by llm-agents, specifically designed for mathematical problem-solving. This model integrates natural language reasoning with external tools like computation libraries and symbolic solvers. It excels at challenging mathematical tasks, achieving 68.8% on GSM8k and 40.1% on MATH datasets. ToRA-7B-v1.0 is optimized for use cases requiring robust mathematical reasoning and tool interaction.

Loading preview...