PaddlePaddle/PaddleOCR-VL

#64 opened 1 day ago by

fgdfbdfbdfsd3

How to set up this on macbook M4

#63 opened 1 day ago by

NatthasitW

docs: Readme Updated for optimized Usage with transformers library

#60 opened 2 days ago by

sayed99

more than 40GB vRAM consumed by paddleocr-vl on A100 GPU!!!

3

#59 opened 3 days ago by

sayed99

how to output a table with ocr as a table

#58 opened 4 days ago by

maaldic

服务端部署

#54 opened 6 days ago by

Alive2June

paddleocr-vl can inferenced by vllm?

#53 opened 6 days ago by

sibylxi

how do convert table OTSL format to HTML format ?

#52 opened 6 days ago by

CCWM

Can't launch the model via docker

#51 opened 6 days ago by

xne0n

PP-DocLayoutV2 没有提供inference.json参数文件，导致ONNX转换失败

#50 opened 7 days ago by

nicozck

Layout Order random

#48 opened 8 days ago by

Chgayot

Layout Analysis Inference

🤝 1

4

#46 opened 9 days ago by

saikanov

Upload yQNWqSPsTxoEXzFZPEWAU.jpeg

#45 opened 9 days ago by

Citrus-777

Not able to run via docker: nvidia-container-cli: initialization error: load library failed: libnvidia-ml.so.1:

#44 opened 10 days ago by

khanfarhan10

PaddleOCR Official Website is Now Live! 🎉

🔥 🚀 4

#43 opened 11 days ago by

ChengCui

ms-swift has supported inference, deployment, and fine-tuning of the PaddleOCR-VL model.

🚀 🔥 7

4

#42 opened 12 days ago by

hu5enpai

执行paddleocr install_genai_server_deps vllm失败

#41 opened 12 days ago by

Hugger819

Help to run PaddleOCR-VL model via Docker

#39 opened 13 days ago by

phamgialinhlx

Need PaddleOCR-VL for lower compute capability

#38 opened 13 days ago by

adnanPBI

Need detailed guide to prepare dataset for fine-tuning

#37 opened 13 days ago by

adnanPBI

docker run failed and how to fix it?

#36 opened 14 days ago by

cbhcba

Set use_doc_preprocessor, but the models for doc preprocessor are not initialized.

7

#35 opened 14 days ago by

Sandstone0525

运行的时候有warning: Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.不影响运行，可以无视吗？

#34 opened 14 days ago by

tarjintor

Can't make it run on Colab

#33 opened 14 days ago by

sanggusti

whats up with all the recent OCR models being released

#30 opened 15 days ago by

evewashere

benchmark with DeepSeek-OCR included

🤗 🚀 9

#29 opened 15 days ago by

jzhang533

A100显卡，如何使用SGLang或VLLM部署

#28 opened 15 days ago by

Alive2June

Đã có ai cài được chưa, sao cài PaddleOCR khó vậy nhỉ, từ cài môi trương win, ubuntu đều lỗi

#27 opened 15 days ago by

dongnchdg

The Kernel crashed, anyone can please help.

10

#24 opened 16 days ago by

ahnulxy

Genunie User Reviews and Questions on Repo PaddlePaddle/PaddleOCR-VL

#23 opened 16 days ago by

DeepNLP

AssertionError: Variable dtype not match, Variable [ linear_164.w_0 ] need tensor with dtype paddle.float32 but load tensor with dtype paddle.bfloat16

➕ 6

#22 opened 16 days ago by

renoyuan

Docker not working on GH 200 with aarch64 cpu architecture

#19 opened 17 days ago by

GodsonLight

没有找到显卡驱动

#18 opened 18 days ago by

wuzhanliai21

Request to add more hardware support

👍 2

#17 opened 18 days ago by

snnh

How to convert charts to table?

#16 opened 18 days ago by

NirajRajai

layoutmodel

#14 opened 18 days ago by

prudant

any possibility to finetune the model ?

#13 opened 18 days ago by

StephennFernandes

where exactly can i find the list of supported languages that this model supports ?

#12 opened 18 days ago by

StephennFernandes

Unrecognized footer

4

#11 opened 18 days ago by

Maguro97

vllm?

#10 opened 18 days ago by

prudant

Enable download counts

#9 opened 18 days ago by

merve

模型在V100上报错

6

#6 opened 19 days ago by

yijinsheng

无法直接通过调用openai compatible api的方式使用？

3

#5 opened 19 days ago by

burrowswang

PaddleOCR-VL Training example

#4 opened 19 days ago by

imneonizer

Only for image? not support PDF?

#3 opened 19 days ago by

stephonye

GGUF or MLX support?

👍 18