Open Source

minimind

A small-scale multimodal vision-language and omni model project designed for fast inference and training on personal GPUs.

Source: GitHub Pricing: Open Source
💻 View Code

About This Project

MiniMind is a series of small-scale open models including MiniMind-V (vision-language) and MiniMind-O (omni-modal). It allows for fast inference and training on personal GPUs, offering fully inspectable end-to-end training pipelines for text, audio, and images.

Tags

LLM multimodal omni-model vlm

Installation & Setup

git clone --depth 1 https://github.com/jingyaogong/minimind-v
pip install -r requirements.txt

Reviews & Ratings

Share your experience

User Reviews (0)

No reviews yet. Be the first to share your experience!