AI models
MiniGPT4 + LRV-Instruction
Parameters
7B
Published
Mar 19, 2024
MiniGPT4 + LRV-Instruction is an AI model developed by University of Maryland and Microsoft (United States), first published in March 2024. 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 7,000,000,000 parameters. It was trained on roughly 6.1M datapoints. Training ran on NVIDIA Quadro RTX 8000.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of MiniGPT4 (Vicuna finetune). Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- University of Maryland, Microsoft
- Country of organization
- United States
- Domain
- Language, Vision, Multimodal
- Task
- Language modeling/generation, Chat, Visual question answering, Image captioning
- Compute estimation method
- Operation counting
- Parameters
- 7,000,000,000
- Dataset size
- 6.1M
- Training hardware
- NVIDIA Quadro RTX 8000
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- MiniGPT4 (Vicuna finetune)
- Epoch confidence
- Speculative
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