HyperCLOVAX-SEED-Vision-Instruct-3B is a 3-billion-parameter multimodal model developed by Naver HyperCLOVA. It combines vision and language capabilities to understand images and follow instructions. The model supports Korean and English and is available on Hugging Face for local inference.
In the Foundation models & chat space, HyperCLOVAX SEED Vision Instruct 3B takes a focused approach. It focuses on understanding images and following natural language instructions in a compact model. It is built as an open-source project for developers. The project is open source (Apache-2.0). It ships for the web, the command line, and API.
It is developed by naver-hyperclovax (South Korea), and it first shipped in 2023.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do