Open Source

MiniCPM-V

MiniCPM-V: A Series of Efficient End-side MLLMs for Vision, Audio and Video

Source: GitHub Pricing: Open Source
💻 View Code

About This Project

MiniCPM-V is a series of end-side multimodal LLMs (MLLMs) designed for vision-language understanding. The models achieve state-of-the-art performance among models of similar sizes.

Tags

mllm multimodal vision

Installation & Setup

git clone https://github.com/OpenBMB/MiniCPM-V.git
cd MiniCPM-V
pip install -r requirements.txt

Reviews & Ratings

Share your experience

User Reviews (0)

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