DenseConnector-v1.5-7B#
README(From Huggingface)#
inference: false license: llama2 pipeline_tag: image-to-text#
DenseConnector-v1.5-7B Model Card#
Model details#
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-v1.5-7B 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 LLaVA-1.5 dataset.
Large Language Model: Vicuna-7B
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/HJYao00/DenseConnector/issues
Intended use#
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.
Model Files#
README.md (1.3 KB)
config.json (1.2 KB)
generation_config.json (170.0 B)
model-00001-of-00003.safetensors (4.6 GB)
model-00002-of-00003.safetensors (4.6 GB)
model-00003-of-00003.safetensors (4.1 GB)
model.safetensors.index.json (75.2 KB)
preprocessor_config.json (393.0 B)
processor/eval/preprocessor_config.json (393.0 B)
sentencepiece.bpe.model (488.0 KB)
special_tokens_map.json (438.0 B)
tokenizer.model (488.0 KB)
tokenizer_config.json (936.0 B)
trainer_state.json (615.1 KB)