AVG-LLaVA Model Card

Model details

Model type: AVG-LLaVA is an open-source LMM that can adaptively select the appropriate visual granularity based on the input image and instruction. It is an auto-regressive language model, based on the transformer architecture. Base LLM: lmsys/vicuna-7b-v1.5

Paper or resources for more information: https://arxiv.org/abs/2410.02745

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/DeepLearnXMU/AVG-LLaVA/issues

Intended use

Primary intended uses: The primary use of 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

• ShareGPT4V Mix665K
• 200K GPT4V-generated instruction data (ALLaVA)
• 200K various VQA data

Evaluation dataset

A collection of 11 benchmarks, including general VQA benchmarks, text-oriented VQA benchmarks, and general multimodal benchmarks.