PaddlePaddle

2026•PaddlePaddle

HPD-Parsing

HPD-Parsing is a lightweight 1B hierarchical parallel document parsing model designed for high-throughput processing of complex document structures. By utilizing a main layout branch for global coordination and localized parallel branches for content generation, it achieves state-of-the-art inference efficiency while maintaining high accuracy.

Hierarchical Parallel Decoding (HPD) for high-throughput, non-sequential generation

Progressive Multi-Token Prediction (P-MTP) to reduce total decoding steps

Staged adaptation pipeline with automated difficulty-aware data curation

PricingFree

RegionChina

2026•PaddlePaddle

PaddleOCR v3.7.0

Open Source

PaddleOCR is an open-source optical character recognition (OCR) toolkit developed by PaddlePaddle, designed to convert images and PDFs into structured data for AI applications. It supports over 100 languages, bridging the gap between visual documents and large language models (LLMs).

Supports over 100 languages

Bridges images/PDFs and LLMs

Open-source and free to use

PricingFree

Version3.7.0

2026•PaddlePaddle

PaddleFormers v1.0

Open Source

LLM

LLMs

PaddleFormers is an easy-to-use library of pre-trained large language models based on PaddlePaddle. It offers a comprehensive collection of models for various natural language processing tasks, facilitating efficient development and deployment.

Pre-trained large language models

Comprehensive model zoo

Easy integration with PaddlePaddle

PricingFree

Version1.0