VLAA-Thinker-Qwen2VL-2B

This model is a vision-language model based on the Qwen2VL architecture, as described in the paper SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models. It takes both image and text as input and generates text as output.

Project Page: https://ucsc-vlaa.github.io/VLAA-Thinking/

Code: https://github.com/UCSC-VLAA/VLAA-Thinking