U
UForm
unum-cloud/UForm
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
★1.2kstars
Python
Apache-2.0
Updated: 6d ago
📋 Project at a Glance
Tap to expand
What's this?Models project leveraging bert and clip, built with Python, open-source
Who made it?Maintained by unum-cloud team, 1.2K⭐ on GitHub, #930 out of 3201 in Models
Why does it exist?As the Models landscape evolved, the unum-cloud team identified the need for better bert solutions. UForm was created to simplify clip workflows.
What can it do?Key use cases: clustering, contrastive-learning, cross-attention
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/unum-cloud/UForm | 官网 https://unum-cloud.github.io/UForm
🔗 github.com/unum-cloud/UForm | 官网 https://unum-cloud.github.io/UForm
Topics
bertclipclusteringcontrastive-learningcross-attentionhuggingface-transformersimage-searchlanguage-visionllavamulti-lingualmultimodalneural-networkopenaiopenclippretrained-modelspytorchrepresentation-learningsemantic-searchtransformervector-search