Qwen2.5-Coder-7B-Instruct

A developer built a 1.5B parameter text-to-SQL model that outperforms a 7B model on the Spider benchmark, achieving 71.5% accuracy through self-consistency voting. The project, starting with Qwen2.5-0…

A new technique called Prompt+Steer, which combines prompting with activation steering, reduces output tokens by an additional ~13% beyond prompting alone on the CodeXGLUE code-to-text task, according…

A developer built a sarcastic AI code reviewer using HTML, CSS, and the open-source Qwen2.5-Coder-7B-Instruct model from Hugging Face. The tool roasts bad markup and praises semantic HTML with dry sar…