all-hands/openhands-lm-7b-v0.1

OpenHands/openhands-lm-7b-v0.1 is a 7.6 billion parameter language model developed by All-Hands, fine-tuned for software engineering tasks. This smaller variant follows the training recipe of the 32B OpenHands LM, leveraging a Qwen Coder 2.5 Instruct base and an RL-based fine-tuning process using OpenHands-generated data. It features a 128K token context window, making it suitable for handling large codebases and long-horizon software development tasks, particularly excelling in resolving GitHub issues.