huggingface / huggingface/optimum-intel

Add support for PaddleOCR-VL-1.5

Open
#1,654 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
620
Forks
270
Avg merge
3d 10h
Merged PRs (30d)
22

Description

Huggingface link: https://huggingface.co/PaddlePaddle/PaddleOCR-VL

The PaddleOCR-VL architecture is already supported by transformers(https://github.com/huggingface/transformers/tree/main/src/transformers/models/paddleocr_vl), but not by optimal-intel.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the PaddleOCR-VL model page and the existing architecture in transformers/models/paddleocr_vl. Then inspect how optimum-intel integrates architectures already supported by Transformers and identify the corresponding validation path. Done means PaddleOCR-VL-1.5 is supported by optimum-intel.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.