Visual Question Answering
Transformers
Safetensors
llava_llama
text-generation
Edit model card


sharegpt4video-8b Model Card

Model details

Model type: sharegpt4video-8b is an open-source video chatbot trained by fine-tuning the entire model on open-source video instruction data. The training process takes around 5 hour on 32xA100 GPUs.

Model date: sharegpt4video-8b was trained in May 2024.

Paper or resources for more information: [Code] [Project Page]

Usage

You can utilize this model as we provide in our [repository].

Training dataset

All training data are open-sourced, you can find the usage in our repository.

  • 153K collection of various video instruction data
  • 28K high-quality video caption data from [ShareGPT4Video]

Intended use

Primary intended uses: The primary use of sharegpt4video-8b is research on large video-language models and video 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.

Paper

arxiv.org/abs/2406.04325

Downloads last month
36,503
Safetensors
Model size
8.35B params
Tensor type
FP16
·
Inference Examples
Inference API (serverless) has been turned off for this model.

Datasets used to train Lin-Chen/sharegpt4video-8b

Spaces using Lin-Chen/sharegpt4video-8b 2

Collection including Lin-Chen/sharegpt4video-8b