🚀 SWE-agent-LM-32B GGUF Models

SWE-agent-LM-32B is a Language Model designed for Software Engineering. It offers an open - source solution trained with the SWE-smith toolkit, aiming to boost the development in software engineering.

✨ Features

• Open Source: SWE-agent-LM-32B is 100% open source, facilitating community contribution and innovation.
• Easy Training: The model was fine - tuned on Qwen 2.5 Coder Instruct with 5k trajectories generated by SWE - agent + Claude 3.7 Sonnet.
• Compatibility: It is compatible with SWE-agent, enabling seamless integration.

📦 Installation

Running this model locally only takes a few steps! Check here for more instructions on how to do so.

📚 Documentation

Model Generation Details

This model was generated using llama.cpp at commit 064cc596.

SWE-agent LM

Code • Paper • Site

SWE-agent-LM-32B is a Language Model for Software Engineering trained using the SWE-smith toolkit. We introduce this model as part of our work: SWE-smith: Scaling Data for Software Engineering Agents.

The training of this model was straightforward. We fine - tuned Qwen 2.5 Coder Instruct on 5k trajectories generated by SWE - agent + Claude 3.7 Sonnet. The dataset can be found here.

Model Information

📄 License

This project is licensed under the apache - 2.0 license.