LLaDA-V / README.md
yyyou's picture
Add library name to model card (#3)
9852b89 verified
metadata
pipeline_tag: image-text-to-text
library_name: transformers

LLaDA-V

We introduce LLaDA-V, a competitive diffusion-based vision-language model, outperforming other diffusion MLLMs.

It was presented in the paper LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning.

Project Page: https://ml-gsai.github.io/LLaDA-V-demo/

Code: https://github.com/ML-GSAI/LLaDA-V