AI models
MiniGPT4 (Vicuna finetune)
Parameters
13B
Published
Oct 2, 2023
MiniGPT4 (Vicuna finetune) is an AI model developed by King Abdullah University of Science and Technology (KAUST) (Saudi Arabia), first published in October 2023. It works in the language, vision and multimodal domain, on tasks such as language modeling/generation, chat, visual question answering and image captioning.
Epoch AI has no training-compute estimate for this model. The model has 13,000,000,000 parameters. It was trained on roughly 1.4B datapoints. Training ran on 4 NVIDIA A100 for about 10 hours.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Vicuna-13B v0. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- King Abdullah University of Science and Technology (KAUST)
- Country of organization
- Saudi Arabia
- Domain
- Language, Vision, Multimodal
- Task
- Language modeling/generation, Chat, Visual question answering, Image captioning
- Compute estimation method
- Hardware
- Parameters
- 13,000,000,000
- Dataset size
- 1.4B
- Training hardware
- NVIDIA A100
- Chips used
- 4
- Training time
- 10 h
- Training power draw
- 3.2 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- Vicuna-13B 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