open-thoughts/OpenThinker3-7B

OpenThinker3-7B by open-thoughts is a 7.6 billion parameter reasoning model, fine-tuned from Qwen2.5-7B-Instruct on the OpenThoughts3-1.2M dataset. This model is specifically optimized for complex reasoning tasks across mathematics, code, and science, demonstrating strong performance against other 7B models. It features a substantial context length of 131072 tokens, making it suitable for detailed problem-solving and analytical applications.