Introducing the github-codereview dataset: A compilation of 200k+ human-written code reviews from top OSS projects (React, Tensorflow, VSCode...).
I finetuned a Qwen2.5-Coder-32B-Instruct model with this dataset and saw significant improvements in generating better code fixes and review comments (4x improved BLEU-4, ROUGE-L, SBERT scores compared to base model).
Introducing the github-codereview dataset: A compilation of 200k+ human-written code reviews from top OSS projects (React, Tensorflow, VSCode...).
I finetuned a Qwen2.5-Coder-32B-Instruct model with this dataset and saw significant improvements in generating better code fixes and review comments (4x improved BLEU-4, ROUGE-L, SBERT scores compared to base model).
Introducing the WebUI dataset: a compilation of screenshot to code pairs of modern websites detailing the styling, framework used, and box bounds for all viewports (Desktop, mobile, tablet).
This dataset showed signs of improved performance in web design LLM benchmarks for a finetuned QWEN 2.5 VL-7B!