Resources

"You are using a model of type deepseek_vl_v2 to instantiate a model of type DeepseekOCR2" Warning

#31 opened 5 days ago by

AndreyPanfilov

什么时候适配50系显卡啊，sm_120，vllm使用也有问题，啥时候支持较新的版本

#30 opened 20 days ago by

xiaotu6e

Is that deepseek-ocr-2 compatible for H200

#29 opened 25 days ago by

balajivasudevan

Add ParseBench evaluation results

#28 opened about 1 month ago by

boyang-runllama

Rename README.md to ebook sur la monétisation de contenu sur Tik tok

#26 opened 2 months ago by

Marquissalomon

Rename README.md to ebook sur la monétisation de contenu sur Tik tok

#25 opened 2 months ago by

Marquissalomon

Duestions about the Stage 1 Encoder Pretraining

#24 opened 2 months ago by

nero2023

config.kv_lora_rank is null?

#23 opened 3 months ago by

SuHu753

元宵节快乐，v4也该来了吧？

#22 opened 3 months ago by

luckjone

How many Language?

#21 opened 3 months ago by

aoiandroid

V4?

#20 opened 3 months ago by

16dvnk

Update conversation.py

#19 opened 3 months ago by

HyzeAI

Add OlmOCRBench evaluation results

#18 opened 3 months ago by

nielsr

📋 Documentation Enhancement Suggestion

#16 opened 4 months ago by

CroviaTrust

📋 Documentation Enhancement Suggestion

#15 opened 4 months ago by

CroviaTrust

The model performs poorly.

#14 opened 4 months ago by

wyb5210

Update README.md

#13 opened 4 months ago by

Lawziet

Update README.md to include the correct Arxiv link instead of linking to the github pdf

#12 opened 4 months ago by

shokrydev

Request a compatible version with newer transformer versions

👀 2

#11 opened 4 months ago by

AliKhajegiliM

Link model to paper and update citation

#10 opened 4 months ago by

nielsr

What do you mean by "novel"? Google has been doing this for ages

👍 1

#9 opened 4 months ago by

davidboring

Analysis on Prompt + Document Type Compatibility

🔥 9

#8 opened 4 months ago by

ysong21

Installation Video and Testing - Step by Step

👍 5

#7 opened 4 months ago by

fahdmirzac

Testing video and colab notebook, Issues with accuracy

👍 1

#6 opened 4 months ago by

ritheshSree

ms-swift has supported inference, deployment, and fine-tuning of the DeepSeek-OCR-2 model.

#5 opened 4 months ago by

hu5enpai

Guide to Run + Fine-tune DeepSeek-OCR 2

🤯❤️ 7

#4 opened 4 months ago by

danielhanchen

Model architectures ['DeepseekOCR2ForCausalLM'] are not supported with latest vllm

#3 opened 4 months ago by

avishekjana

Made a Demo for people who want to quickly try the model

#2 opened 4 months ago by

ysong21

Compare to LightOnOCR-2-1B

#1 opened 4 months ago by

staghado