ViP-LLaVA Model Card
Model details
Model type: ViP-LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on both image level instruction data and region-level instruction data annotated with visual prompts. It is an auto-regressive language model, based on the transformer architecture.
Model date: ViP-LLaVA-7B-Refcocog-ft was trained in November 2023. Paper
Paper or resources for more information: https://vip-llava.github.io/
License
Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
Where to send questions or comments about the model: https://github.com/mu-cai/ViP-LLaVA/issues
Intended use
Primary intended uses: The primary use of ViP-LLaVA is research on large multimodal models and chatbots.
Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
Training dataset
- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
Evaluation dataset
ViP-LLaVA achieves state-of-the-art performance in 4 academic region-level benchmarks and our newly proposed RegionBench.
- Downloads last month
- 8