GSAI-ML/LLaDA-8B-Instruct
We introduce LLaDA, a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance. [Project Page](https://ml-gsai.github.io/LLaDA-demo/) [Code](https://github.com/ML-GSAI/LLaDA) [2025-10-21] We have modified modeling_llada.py to support the input of attention_mask.
Parameters
8B
Modality
text->text
License
mit
Open source
Yes
Open GSAI-ML/LLaDA-8B-Instruct in AIniverse
Compare versions, read real ratings, save to your stack.
Open in App