AI models
LLaVA + LVIS-INSTRUCT4V
Parameters
13B
Published
Nov 13, 2023
LLaVA + LVIS-INSTRUCT4V is an AI model developed by Fudan University and University of Maryland (China and United States), first published in November 2023. It works in the multimodal, language and vision domain, on tasks such as language modeling/generation and visual question answering.
Epoch AI has no training-compute estimate for this model. The model has 13,000,000,000 parameters.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of LLaVA 1.5. The reference paper has 148 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Fudan University, University of Maryland
- Country of organization
- China, United States
- Domain
- Multimodal, Language, Vision
- Task
- Language modeling/generation, Visual question answering
- Parameters
- 13,000,000,000
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- LLaVA 1.5
- Citations
- 148
- Epoch confidence
- Likely
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