deepseek-ai
/

DeepSeek-OCR

Image-Text-to-Text

vision-language

Model card Files Files and versions

Resources

View closed (2)

DeepSeek-OCR running in google colab

#27 opened about 9 hours ago by

🚀测评视频

#26 opened about 11 hours ago by

Quick docker compose setup + vibe coded app to leverage it - very rough!

#25 opened about 12 hours ago by

add GGUF model for ollama inference

#24 opened about 12 hours ago by

add streamer for infer method when not eval mode

#23 opened about 13 hours ago by

ocr

#22 opened about 19 hours ago by

fixing hardcoded cuda() for cpu inference

#21 opened about 21 hours ago by

alexgambashidze

mps support

#20 opened about 23 hours ago by

训练数据开源

#19 opened about 23 hours ago by

Clarifying Prior Research on Visual Compression of Textual Contexts

#18 opened 1 day ago by

Missing Arxiv link?

#17 opened 1 day ago by

Benchmarks?

#16 opened 1 day ago by

vllm across serving open api compatible api?

#15 opened 1 day ago by

Local Installation Video and Testing - Step by Step

#13 opened 1 day ago by

List of possible label types?

#11 opened 1 day ago by

Delete .ipynb_checkpoints/README-checkpoint.md (Duplicate, Junk)

#10 opened 1 day ago by

Gradio app

#9 opened 1 day ago by

Colab Demo Video and Hallucination issues

#8 opened 1 day ago by

Flash attention issue with python 3.13

#7 opened 1 day ago by

Make infer general, so it runs on non cuda devices

#6 opened 1 day ago by

Adding `transformers` as the library name

#5 opened 1 day ago by

code quality

#4 opened 2 days ago by

Mac support

#3 opened 2 days ago by

agi

#2 opened 2 days ago by

Possibilities of QAT model versions?

#1 opened 2 days ago by