deepseek-ai/DeepSeek-OCR

Bboxes

#58 opened about 2 hours ago by

mubashiross

finetune ?

#57 opened about 2 hours ago by

winzzniw555

how to use deep-seek-ocr model

#56 opened about 2 hours ago by

Zhaleh197

How to use it correctly with online serving via vllm openai compatible server?

1

#55 opened about 4 hours ago by

dhruvil237

Remove hardcoded .cuda() calls to support single forward pass on CPU and ensure DeepSeekOCR model compatibility with transformers==4.52.4

#54 opened about 7 hours ago by

kamalrajkannanmcw

🧠 Why does DeepSeek-OCR not use Multi-Head Latent Attention (MLA)?

1

#53 opened about 9 hours ago by

ZoneTwelve

Upload _cd6c77db-a9ab-4574-bc8e-bcf418df9b5c.jpg

#51 opened about 21 hours ago by

DanniS89

How can I use this model with vLLM and send requests to it via an API?

👀 3

1

#50 opened 1 day ago by

123fsafdfhdhfg

Can i pull a best model after train for self host

#49 opened 1 day ago by

pot030321

Can this model run on Ascend NPU?

#48 opened 1 day ago by

Evoenzo

Upload yQNWqSPsTxoEXzFZPEWAU (1).jpeg

#47 opened 2 days ago by

Citrus-777

🚩 Report: Spam

#46 opened 3 days ago by

Vansh1823

Rpp

#45 opened 4 days ago by

Unknown010104

Update README.md

#44 opened 4 days ago by

Jalea96

Update README.md

1

#43 opened 4 days ago by

Melskay

Adding transformers as the library name

#42 opened 4 days ago by

ariG23498

ajkhjjha

#41 opened 4 days ago by

djhajhk

Update README.md

#40 opened 5 days ago by

krecceg

Hello

1

#39 opened 5 days ago by

anmolkumarjha

Make compatible with newer transformers

🤗 5

2

#38 opened 5 days ago by

harpreetsahota

coordinates of bounding boxes along with confidences

👍 1

1

#36 opened 5 days ago by

SWAGATAM041

Genuine User Reviews and Questions on Repo deepseek-ai/DeepSeek-OCR

#35 opened 5 days ago by

DeepNLP

Can I ask it to do image classification?

🧠 1

3

#34 opened 5 days ago by

allen7575

PDF recognition often misses several pages.

#33 opened 6 days ago by

xldistance

Podcast on the paper

❤️ 1

#32 opened 6 days ago by

dcaustin33

What are the minimal computer/server config (memory, processor, GPU) to run DeepSeek-OCR?

2

#31 opened 6 days ago by

leandrobortolotto

Deepseek OCR WebUI supports image and PDF file recognition.

4

#30 opened 6 days ago by

xldistance

Improve model card: add `library_name`, refine `pipeline_tag`, add HF paper and project links

1

#29 opened 6 days ago by

nielsr

DeepSeek-OCR in DeepSeek Chat?

2

#28 opened 7 days ago by

Ligant

DeepSeek-OCR running in google colab

😎 👍 8

11

#27 opened 7 days ago by

Javedalam

🚀测评视频

#26 opened 7 days ago by

leo009

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

#25 opened 7 days ago by

moggers

add GGUF model for ollama inference

👍 41

3

#24 opened 7 days ago by

bored10

add streamer and verbose params and image_file support io.ByteIO,PIL.Image.Image for infer method

🔥 1

#23 opened 7 days ago by

weege007

ocr

#22 opened 7 days ago by

xwq777

fixing hardcoded cuda() for cpu inference

❤️ 3

4

#21 opened 7 days ago by

alexgambashidze

mps support

👍 12

20

#20 opened 8 days ago by

arcaputo3

训练数据开源

❤️ 🤯 7

6

#19 opened 8 days ago by

renchang

Clarifying Prior Research on Visual Compression of Textual Contexts

❤️ 👍 13

#18 opened 8 days ago by

Awiny

Missing Arxiv link?

😔 5

1

#17 opened 8 days ago by

RoversX

Benchmarks?

👍 4

#16 opened 8 days ago by

nahsor

vllm across serving open api compatible api?

👍 ❤️ 1

2

#15 opened 8 days ago by

prudant

Local Installation Video and Testing - Step by Step

👍 1

#13 opened 8 days ago by

fahdmirzac

List of possible label types?

#11 opened 8 days ago by

selimc

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

#10 opened 8 days ago by

qpqpqpqpqpqp

Gradio app

🚀 2

6

#9 opened 8 days ago by

freakynit

Colab Demo Video and Hallucination issues

🔥 2

1

#8 opened 8 days ago by

ritheshSree

Flash attention issue with python 3.13

2

#7 opened 8 days ago by

freakynit

Make infer general, so it runs on non cuda devices

🤝 3

1

#6 opened 8 days ago by

aamirshakir

code quality

1

#4 opened 8 days ago by

J22