AI models
Wu Dao - Wen Hui
Training compute
1.2×10²⁰ FLOP
Parameters
11.3B
Published
Mar 1, 2021
Wu Dao - Wen Hui is an AI model developed by Beijing Academy of Artificial Intelligence / BAAI (China), first published in March 2021. It works in the language, multimodal, video and image generation domain, on tasks such as language modeling/generation, image generation, video generation and 3 more.
Training it took an estimated 1.2×10²⁰ FLOP of compute (estimation method: hardware). The model has 11,300,000,000 parameters. Training ran on 64 NVIDIA V100 for about 60 hours.
Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Beijing Academy of Artificial Intelligence / BAAI
- Country of organization
- China
- Domain
- Language, Multimodal, Video, Image generation
- Task
- Language modeling/generation, Image generation, Video generation, Text-to-image, Question answering, Visual question answering
- Training compute
- 1.2×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 11,300,000,000
- Training hardware
- NVIDIA V100
- Chips used
- 64
- Training time
- 60 h
- Training power draw
- 38.9 kW
- Epoch confidence
- Confident
More from Beijing Academy of Artificial Intelligence / BAAI
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models