AI models
Baichuan-Omni
Parameters
7B
Published
Oct 11, 2024
Baichuan-Omni is an AI model developed by Baichuan, Westlake University and Zhejiang University (ZJU) (China), first published in October 2024. It works in the language, vision, multimodal and 3 more domain, on tasks such as visual question answering, language modeling/generation, video description and 2 more.
Epoch AI has no training-compute estimate for this model. The model has 7,000,000,000 parameters.
Access: Unreleased. Its weights are not openly released. The reference paper has 35 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Baichuan, Westlake University, Zhejiang University (ZJU)
- Country of organization
- China
- Domain
- Language, Vision, Multimodal, Audio, Speech, Video
- Task
- Visual question answering, Language modeling/generation, Video description, Speech synthesis, Image captioning
- Parameters
- 7,000,000,000
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 35
- Epoch confidence
- Confident
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