Skip to main content

Easy-to-use and powerful NLP library with Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including Neural Search, Question Answering, Information Extraction and Sentiment Analysis end-to-end system.

Project description

简体中文🀄 | English🌎

Features | Installation | Quick Start | API Reference | Community

PaddleNLP is a NLP library that is both easy to use and powerful. It aggregates high-quality pretrained models in the industry and provides a plug-and-play development experience, covering a model library for various NLP scenarios. With practical examples from industry practices, PaddleNLP can meet the needs of developers who require flexible customization.

News 📢

  • 2023.6.12: Release of PaddleNLP v2.6rc

  • 2023.1.12: Release of PaddleNLP v2.5

    • 🔨 NLP Tools: PPDiffusers, our cross-modal diffusion model toolbox based on PaddlePaddle, has been released! It provides a complete training process for diffusion models, and supports FastDeploy inference acceleration and multi-hardware deployment (supports Ascend chips and Kunlun core deployment).
    • 💎 Industrial Applications: Information extraction, text classification, sentiment analysis, and intelligent question answering have all been newly upgraded. New releases include document information extraction UIE-X, unified text classification UTC, unified sentiment analysis UIE-Senta , and unsupervised QA application. At the same time, the ERNIE 3.0 Tiny v2 series of pretrained small models have been released, which are more effective with low-resource and foreign data. They provide open-source end-to-end deployment solutions such as model pruning, model quantization, FastDeploy inference acceleration, and edge-side deployment to reduce the difficulty of pretrained model deployment.
    • 💪 Framework Upgrade: Pretrained model parameter configuration unification, saving and loading custom parameter configurations no longer requires additional development; Trainer API has added BF16 training, recompute recalculations, sharding, and other distributed capabilities. Large-scale pre-training model training can easily be accomplished through simple configuration. Model Compression API supports quantization training, vocabulary compression, and other functions. The compressed model has smaller accuracy loss, and the memory consumption of model deployment is greatly reduced. Data Augmentation API has been comprehensively upgraded to support three granularities of data augmentation strategy: character, word, and sentence, making it easy to customize data augmentation strategies.
    • 🤝 Community: 🤗Huggingface hub officially supports PaddleNLP pretrained models, supporting PaddleNLP Model and Tokenizer downloads and uploads directly from the 🤗Huggingface hub. Everyone is welcome to try out PaddleNLP pretrained models on the 🤗Huggingface hub here.
  • September 6, 2022: Release of PaddleNLP v2.4

    • 🔨 NLP Tools: NLP Pipeline System Pipelines has been released, supporting the rapid construction of search engines and question-answering systems, and can be extended to support various NLP systems, making it easy, flexible, and efficient to solve NLP tasks like building blocks!
    • 💎 Industrial Applications: A new text classification full-process application solution has been added, covering various scenarios such as multi-classification, multi-label, and hierarchical classification, supporting small-sample learning and TrustAI trustworthy computing model training and tuning.
    • 🍭 AIGC: The SOTA model CodeGen for code generation in various programming languages has been added.
    • 💪 Framework Upgrade: Automatic Model Compression API has been released, which automatically cuts and quantizes models, greatly reducing the threshold for using model compression technology. Few-shot Prompt capability has been released, integrating classic algorithms such as PET, P-Tuning, and RGL.


📦 Out-of-Box NLP Toolset

🤗 Awesome Chinese Model Zoo

🎛️ Industrial End-to-end System

🚀 High Performance Distributed Training and Inference

Out-of-Box NLP Toolset

Taskflow aims to provide off-the-shelf NLP pre-built task covering NLU and NLG technique, in the meanwhile with extremely fast inference satisfying industrial scenario.


For more usage please refer to Taskflow Docs.

Awesome Chinese Model Zoo

🀄 Comprehensive Chinese Transformer Models

We provide 45+ network architectures and over 500+ pretrained models. Not only includes all the SOTA model like ERNIE, PLATO and SKEP released by Baidu, but also integrates most of the high-quality Chinese pretrained model developed by other organizations. Use AutoModel API to ⚡SUPER FAST⚡ download pretrained models of different architecture. We welcome all developers to contribute your Transformer models to PaddleNLP!

from paddlenlp.transformers import *

ernie = AutoModel.from_pretrained('ernie-3.0-medium-zh')
bert = AutoModel.from_pretrained('bert-wwm-chinese')
albert = AutoModel.from_pretrained('albert-chinese-tiny')
roberta = AutoModel.from_pretrained('roberta-wwm-ext')
electra = AutoModel.from_pretrained('chinese-electra-small')
gpt = AutoModelForPretraining.from_pretrained('gpt-cpm-large-cn')

Due to the computation limitation, you can use the ERNIE-Tiny light models to accelerate the deployment of pretrained models.

# 6L768H
ernie = AutoModel.from_pretrained('ernie-3.0-medium-zh')
# 6L384H
ernie = AutoModel.from_pretrained('ernie-3.0-mini-zh')
# 4L384H
ernie = AutoModel.from_pretrained('ernie-3.0-micro-zh')
# 4L312H
ernie = AutoModel.from_pretrained('ernie-3.0-nano-zh')

Unified API experience for NLP task like semantic representation, text classification, sentence matching, sequence labeling, question answering, etc.

import paddle
from paddlenlp.transformers import *

tokenizer = AutoTokenizer.from_pretrained('ernie-3.0-medium-zh')
text = tokenizer('natural language processing')

# Semantic Representation
model = AutoModel.from_pretrained('ernie-3.0-medium-zh')
sequence_output, pooled_output = model(input_ids=paddle.to_tensor([text['input_ids']]))
# Text Classificaiton and Matching
model = AutoModelForSequenceClassification.from_pretrained('ernie-3.0-medium-zh')
# Sequence Labeling
model = AutoModelForTokenClassification.from_pretrained('ernie-3.0-medium-zh')
# Question Answering
model = AutoModelForQuestionAnswering.from_pretrained('ernie-3.0-medium-zh')

Wide-range NLP Task Support

PaddleNLP provides rich examples covering mainstream NLP task to help developers accelerate problem solving. You can find our powerful transformer Model Zoo, and wide-range NLP application examples with detailed instructions.

Also you can run our interactive Notebook tutorial on AI Studio, a powerful platform with FREE computing resource.

PaddleNLP Transformer model summary (click to show details)
Model Sequence Classification Token Classification Question Answering Text Generation Multiple Choice

For more pretrained model usage, please refer to Transformer API Docs.

Industrial End-to-end System

We provide high value scenarios including information extraction, semantic retrieval, question answering high-value.

For more details industrial cases please refer to Applications.

🔍 Neural Search System

For more details please refer to Neural Search.

❓ Question Answering System

We provide question answering pipeline which can support FAQ system, Document-level Visual Question answering system based on 🚀RocketQA.

For more details please refer to Question Answering and Document VQA.

💌 Opinion Extraction and Sentiment Analysis

We build an opinion extraction system for product review and fine-grained sentiment analysis based on SKEP Model.

For more details please refer to Sentiment Analysis.

🎙️ Speech Command Analysis

Integrated ASR Model, Information Extraction, we provide a speech command analysis pipeline that show how to use PaddleNLP and PaddleSpeech to solve Speech + NLP real scenarios.

For more details please refer to Speech Command Analysis.

High Performance Distributed Training and Inference

⚡ FastTokenizer: High Performance Text Preprocessing Library

AutoTokenizer.from_pretrained("ernie-3.0-medium-zh", use_fast=True)

Set use_fast=True to use C++ Tokenizer kernel to achieve 100x faster on text pre-processing. For more usage please refer to FastTokenizer.

⚡ FastGeneration: High Performance Generation Library

model = GPTLMHeadModel.from_pretrained('gpt-cpm-large-cn')
outputs, _ = model.generate(
    input_ids=inputs_ids, max_length=10, decode_strategy='greedy_search',

Set use_fast=True to achieve 5x speedup for Transformer, GPT, BART, PLATO, UniLM text generation. For more usage please refer to FastGeneration.

🚀 Fleet: 4D Hybrid Distributed Training

For more super large-scale model pre-training details please refer to GPT-3.



  • python >= 3.7
  • paddlepaddle >= 2.3

More information about PaddlePaddle installation please refer to PaddlePaddle's Website.

Python pip Installation

pip install --upgrade paddlenlp

or you can install the latest develop branch code with the following command:

pip install --pre --upgrade paddlenlp -f

Quick Start

Taskflow aims to provide off-the-shelf NLP pre-built task covering NLU and NLG scenario, in the meanwhile with extremely fast inference satisfying industrial applications.

from paddlenlp import Taskflow

# Chinese Word Segmentation
seg = Taskflow("word_segmentation")
>>> ['第十四届', '全运会', '在', '西安', '举办']

# POS Tagging
tag = Taskflow("pos_tagging")
>>> [('第十四届', 'm'), ('全运会', 'nz'), ('在', 'p'), ('西安', 'LOC'), ('举办', 'v')]

# Named Entity Recognition
ner = Taskflow("ner")
>>> [('《', 'w'), ('孤女', '作品类_实体'), ('》', 'w'), ('是', '肯定词'), ('2010年', '时间类'), ('九州出版社', '组织机构类'), ('出版', '场景事件'), ('的', '助词'), ('小说', '作品类_概念'), (',', 'w'), ('作者', '人物类_概念'), ('是', '肯定词'), ('余兼羽', '人物类_实体')]

# Dependency Parsing
ddp = Taskflow("dependency_parsing")
>>> [{'word': ['9月9日', '上午', '纳达尔', '在', '亚瑟·阿什球场', '击败', '俄罗斯', '球员', '梅德韦杰夫'], 'head': [2, 6, 6, 5, 6, 0, 8, 9, 6], 'deprel': ['ATT', 'ADV', 'SBV', 'MT', 'ADV', 'HED', 'ATT', 'ATT', 'VOB']}]

# Sentiment Analysis
senta = Taskflow("sentiment_analysis")
>>> [{'text': '这个产品用起来真的很流畅,我非常喜欢', 'label': 'positive', 'score': 0.9938690066337585}]

API Reference

  • Support LUGE dataset loading and compatible with Hugging Face Datasets. For more details please refer to Dataset API.
  • Using Hugging Face style API to load 500+ selected transformer models and download with fast speed. For more information please refer to Transformers API.
  • One-line of code to load pre-trained word embedding. For more usage please refer to Embedding API.

Please find all PaddleNLP API Reference from our readthedocs.



To connect with other users and contributors, welcome to join our Slack channel.


Scan the QR code below with your Wechat⬇️. You can access to official technical exchange group. Look forward to your participation.


If you find PaddleNLP useful in your research, please consider cite

    title={PaddleNLP: An Easy-to-use and High Performance NLP Library},
    author={PaddleNLP Contributors},
    howpublished = {\url{}},


We have borrowed from Hugging Face's Transformers🤗 excellent design on pretrained models usage, and we would like to express our gratitude to the authors of Hugging Face and its open source community.


PaddleNLP is provided under the Apache-2.0 License.

Project details

Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

paddlenlp-2.7.2.tar.gz (2.2 MB view hashes)

Uploaded source

Built Distribution

paddlenlp-2.7.2-py3-none-any.whl (2.8 MB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page