inference: false
pipeline_tag: image-text-to-text
LLaVA Model Card
Model details
Model type: Follows LLaVA, CCA-LLaVA(arxiv.org/abs/2410.15926) is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.
Model date: CCA-LLaVA-v1.5-7B was trained in April 2024.
Paper or resources for more information: https://github.com/xing0047/cca-llava.git
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/xing0047/cca-llava/issues
Intended use
Primary intended uses: The primary use of CCA-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.
- 158K GPT-generated multimodal instruction-following data.
- 450K academic-task-oriented VQA data mixture.
- 40K ShareGPT data.
Evaluation dataset
A collection of 8 benchmarks, including 3 visual hallucination benchmarks and 5 recent benchmarks specifically proposed for instruction-following LMMs.