Multimodal model

typhoon-ocr-3b

Listed for image text to text. Explore the model card for usage and requirements.

Type
Multimodal
Weights
Open
Downloads
147k
Likes
10
Pipeline
image text to text
License
apache-2.0

Model hub

typhoon-ai/typhoon-ocr-3b

Repo
typhoon-ai/typhoon-ocr-3b
Library
transformers
Access
Public
Technical tags and languages
en th transformers safetensors qwen2_5_vl image-text-to-text OCR vision-language document-understanding multilingual conversational base_model:Qwen/Qwen2.5-VL-3B-Instruct base_model:finetune:Qwen/Qwen2.5-VL-3B-Instruct text-generation-inference
Open on Hugging Face

Papers

1

More from typhoon-ai

2