Gpt-4V Open Source Alternative

open-source

GPT-4V alternatives

Llama3-v

MiniCPM-V

Video-LLaVA

InternVL

CogVLM2

PaliGemma

multimodal tasks

This article discusses open-source alternatives to GPT-4V, such as Llama3-v, MiniCPM-V, Video-LLaVA, InternVL, CogVLM2, and PaliGemma. These alternatives are specifically designed for multimodal tasks and provide more information about their usage through the provided links.

Published

May 21, 2024

with llama3-v inside

https://github.com/OpenBMB/MiniCPM-V

https://github.com/mbzuai-oryx/Video-LLaVA

https://github.com/OpenGVLab/InternVL

https://github.com/THUDM/CogVLM2

PaliGemma (multimodal) from Google:

https://hf-mirror.com/google/paligemma-3b-pt-224

https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md

https://github.com/huggingface/blog/blob/main/paligemma.md

lots of open source models can be found at:

https://hf-mirror.com/google