G
Groma
FoundationVision/Groma
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
★585stars
Python
Apache-2.0
Updated: 3w ago
📋 Project at a Glance
Tap to expand
What's this?A , built with Python open-source project in the Models category, core strengths: foundation-models/grounding
Who made it?Maintained by FoundationVision team, 585⭐ on GitHub, #1654 out of 3201 in Models
Why does it exist?With the growing demand for foundation-models and grounding in Models, FoundationVision created Groma as a streamlined solution.
What can it do?Key use cases: large-language-models, llama, llama2
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/FoundationVision/Groma | 官网 https://groma-mllm.github.io/
🔗 github.com/FoundationVision/Groma | 官网 https://groma-mllm.github.io/
Topics
foundation-modelsgroundinglarge-language-modelsllamallama2llmmllmmultimodalvision-language-model