open-thoughts/OpenThinker-Agent-v1-SFT

OpenThinker-Agent-v1-SFT is an 8 billion parameter language model developed by OpenThoughts, fine-tuned from Qwen3-8B with a 32K context length. This model represents the supervised fine-tuning (SFT) stage of the OpenThinker-Agent-v1 series, specifically optimized for agentic tasks like Terminal-Bench 2.0 and SWE-Bench. It is designed to excel in environments requiring complex task execution and problem-solving through shell commands and bug fixing.