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

Downloads last month
1,421
Safetensors
Model size
8.43B params
Tensor type
F16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support