Skip to content

bigdefence

Midm-2.0-Mini-Vision-Instruct

bigdefence/Midm-2.0-Mini-Vision-Instruct

Midm-2.0-Mini-Vision-Instruct is a image-to-text model from bigdefence. Use it when you need a caption or text from an image. The card lists the license as apache-2.0.

- Midm-2.0-Mini-Vision-Instruct은 Midm-2.0-Mini-Vision-Instruct은 한국어 이미지 인식에 특화된 고성능, 경량 Vision-Language Model입니다. K-intelligence/Midm-2.0-Mini-Instruct 기반으로 구축되어 한국어 텍스트가 포함된 이미지 이해와 한국어 응답 생성에 최적화되었습니다. - End-to-End…

Downloads · 30 days

9

4% of all-time downloads

All-time downloads

212

Public

Parameters

2.6B

5.2 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors5.2 GB · 100%

At a glance

Task
Image-to-Text
License
apache-2.0
Model type
llava_midm
Access
Public
Created
Aug 27, 2025
Updated
Aug 29, 2025
SHA
46e8bd04

Base models

Task
Image-to-Text
Type
llava_midm
License
apache-2.0
Languages
ko
Created
Aug 27, 2025
Updated
Aug 29, 2025
Midm-2.0-Mini-Vision-Instruct — AI Model — AIMarketly