VOOZH about

URL: https://huggingface.co/GSAI-ML/LLaDA-8B-Base

⇱ GSAI-ML/LLaDA-8B-Base · Hugging Face


LLaDA-8B-Base

We introduce LLaDA, a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance.

Project Page

Code

Updates

[2025-10-21] We have modified modeling_llada.py to support the input of attention_mask.

Downloads last month
101,562
Safetensors
Model size
8B params
Tensor type
BF16
·

Model tree for GSAI-ML/LLaDA-8B-Base

Adapters
20 models
Finetunes
17 models
Quantizations
4 models

Spaces using GSAI-ML/LLaDA-8B-Base 4