GSAI-ML/LLaDA-8B-InstructLLaDA 8B Instruct 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.

LLaDA-8B-Instruct

PUBLIC

Mirrored

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

Tasks:text-generationLibraries:transformersLicense:mit

imported

huggingface

minio

transformers

safetensors

llada

text-generation

conversational

custom_code

license:mit

eval-results

region:us

383.5Kdownloads359likestransformersLicense:mit

Model Card

Edit

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

Code

Updates

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

Inference ProvidersText Generation

Your message…

This model isn't deployed by any Inference Provider yet. Deploy this model →

Safetensors details

Format

Safetensors

Model size

8B params

Tasks

text-generation

Source

Mirrored from an external registry.

Last synced 7/28/2026

Commit History

No commits available

We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy