AI models
GroundingGPT
Parameters
7B
Published
Mar 5, 2024
GroundingGPT is an AI model developed by ByteDance and Fudan University (China), first published in March 2024. It works in the multimodal, language, video and 2 more domain, on tasks such as chat, language modeling/generation, image embedding and 3 more.
Epoch AI has no training-compute estimate for this model. The model has 7,000,000,000 parameters. Training ran on 8 NVIDIA A100.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Vicuna-7B v0. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- ByteDance, Fudan University
- Country of organization
- China
- Domain
- Multimodal, Language, Video, Vision, Speech
- Task
- Chat, Language modeling/generation, Image embedding, Image captioning, Video description, Speech recognition (ASR)
- Parameters
- 7,000,000,000
- Training hardware
- NVIDIA A100
- Chips used
- 8
- Training power draw
- 6.3 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- Vicuna-7B v0
- 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