Skip to main content

Tiny GPTV - Pytorch

Project description

Multi-Modality

TinyGPTV

Simple Implementation of TinyGPTV in super simple Zeta lego blocks. Here all the modules from figure 2 are implemented in Zeta and Pytorch

Usage

import torch
from tiny_gptv import TinyGPTVBlock

x = torch.rand(2, 8, 512)
lora_mha = TinyGPTVBlock(512, 8)
out = lora_mha(x)
print(out.shape)

Citation

@misc{yuan2023tinygptv,
    title={TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones}, 
    author={Zhengqing Yuan and Zhaoxu Li and Lichao Sun},
    year={2023},
    eprint={2312.16862},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tiny_gptv-0.0.1.tar.gz (3.4 kB view hashes)

Uploaded Source

Built Distribution

tiny_gptv-0.0.1-py3-none-any.whl (3.2 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page