TYPHOON 2 Vision
General
Qwen2-VL
7B
Vision-optimized model with advanced OCR capabilities for Thai documents and visual question answering.
Released
January 9, 2025
Context
up to 32K tokens
Input
Image
Output
Text
About this Model
[Research Preview] A model optimized for visual data, featuring advanced OCR capabilities for Thai documents, Chart VQA, and more. It enables highly accurate text extraction and context-aware reasoning for tasks like document understanding and visual question answering.
Key Features
Enhanced Visual Understanding
Interprets complex images and integrates them with text for robust multimodal task performance.
Bilingual Optimization
Uses translation and distillation techniques for superior Thai document understanding with high visual and contextual accuracy.
Image-Centric Optimization
TYPHOON2-Vision is specifically fine-tuned for image-based tasks with strong instruction-following capabilities.
Release History
Version 1
January 9, 2025
Initial release
Availability
TYPHOON API
Not available
TYPHOON API Pro
Not available
Other Platforms
Not available
Related Links