HyperCLOVAX-SEED-Vision-Instruct-3B

Original model: https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B
Use https://github.com/NAVER-Cloud-HyperCLOVA-X/llama.cpp (llama.cpp fork with support for HyperCLOVA X models)

Quick start

llama-mtmd-cli -hf naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B-GGUF --image image.jpg -p "이미지 설명해줘"

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for naver-ellm/HyperCLOVAX-SEED-Vision-Instruct-3B-GGUF

Base model

Quantized

(1)

this model