SWE-bench/SWE-agent-LM-7B

SWE-agent-LM-7B is a 7.6 billion parameter language model developed by the SWE-bench team, specifically fine-tuned for software engineering tasks. It was trained using the SWE-smith toolkit on 5,000 trajectories generated by SWE-agent + Claude 3.7 Sonnet, making it highly optimized for agentic software development workflows. This model is designed for compatibility with SWE-agent and excels at automating code-related tasks.