01

Basic information

Model repository: unsloth/DeepSeek-OCR-2
Organization: unsloth
Tasks: image-text-to-text

02

Architecture and runtime

Model type: deepseek_vl_v2
Architecture: DeepseekOCR2ForCausalLM
Libraries: pytorch, transformer, safetensors
Base models: deepseek-ai/DeepSeek-OCR-2
Current revision: master

03

License and update history

License: apache-2.0
Created: 2026-02-03
Last updated: 2026-06-17

deepseekunslothvision-languageocrcustom_code
04

Hardware requirements

Not filled in locally.

05

Download links

Not filled in locally.

06

Basic usage example

Not filled in locally.