Show HN: 4B VLM trained on 600k questions to query images in one pass
https://github.com/aditmag/dragonfly
Heyo!I'm Adit, an undergrad in Finland. This is a preview of a side project I worked on last weekend. Essentially, Dragonfly is a LoRA fine-tune of Qwen3-VL with typed output heads that answers many questions about an image in one pass, with a probability for every answer. Unlike a VLM that generates an answer to each question, Dragonfly reads the image once and scores every question in the...