Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
deepseek-ai
/
DeepSeek-OCR
like
2.98k
Follow
DeepSeek
111k
Image-Text-to-Text
Transformers
Safetensors
multilingual
deepseek_vl_v2
feature-extraction
deepseek
vision-language
ocr
custom_code
arxiv:
2510.18234
License:
mit
Model card
Files
Files and versions
xet
Community
103
Deploy
Use this model
【问题反馈】GaoDa-M 模式下动态预处理未正确使用 1024×1024，仍固定为 640×640 问题描述
#84
by
liushihowe
- opened
Nov 13
Discussion
liushihowe
Nov 13
This comment has been hidden (marked as Resolved)
Edit
Preview
Upload images, audio, and videos by dragging in the text input, pasting, or
clicking here
.
Tap or paste here to upload images
Comment
·
Sign up
or
log in
to comment
