Model type: DenseConnector 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 info: DenseConnector-with-mgm-7B was trained in 05/2024.

Paper or resources for more information: https://github.com/HJYao00/DenseConnector

Paper on Hugging Face: arxiv.org/abs/2405.13800

Training dataset: This model is trained on MGM dataset.

Large Language Model: Vicuna-7B

How to inference: This model was trained based on the MGM codebase. Please replace mgm_arch.py in MGM to test our model.

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/HJYao00/DenseConnector/issues

Primary intended uses: The primary use of DenseConnector 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.