AIBase
Home
AI NEWS
AI Tools
AI Models
MCP
AI Services
AI Compute
AI Tutorial
Datasets
EN

AI News

View More

Challenging Conventional Wisdom! Ant Group and Renmin University to Launch the First Native MoE Diffusion Language Model in the Industry at the 2025 Bund Conference

Ant Group and Renmin University developed LLaDA-MoE, a native MoE-based diffusion language model trained on 20T data, demonstrating scalability and stability. It outperforms LLaDA1.0/1.5 and Dream-7B, rivals autoregressive models with faster inference. The model will be open-sourced soon.....

7.7k 5 hours ago
Challenging Conventional Wisdom! Ant Group and Renmin University to Launch the First Native MoE Diffusion Language Model in the Industry at the 2025 Bund Conference

Models

View More

LLaDA MoE 7B A1B Base

inclusionAI

L

LLaDA-MoE is a new type of mixture-of-experts language model constructed based on the diffusion principle. It is the first open-source MoE diffusion large language model, pre-trained from scratch on approximately 20 trillion tokens. It has a total of 7 billion parameters, and only 1.4 billion parameters are activated during inference. It performs excellently in tasks such as code generation and mathematical reasoning.

Natural Language ProcessingTransformersTransformers
inclusionAI
1.2k
20
AIBase
Empowering the future, your artificial intelligence solution think tank
English简体中文繁體中文にほんご
FirendLinks:
AI Newsletters AI ToolsMCP ServersAI NewsAIBaseLLM LeaderboardAI Ranking
© 2025AIBase
Business CooperationSite Map