🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

TensorFlow code and pre-trained models for BERT

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

100+ Chinese Word Vectors 上百种预训练中文词向量

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。

keras implement of transformers for humans

PyMongo - the Official MongoDB Python driver

Lingvo

Implementation of BERT that could load official pre-trained models for feature extraction and prediction

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Python's Filesystem abstraction layer

novel deep learning research works with PaddlePaddle

Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）

Knowledge Graph,Question Answering System，基于知识图谱和向量检索的医疗诊断问答系统

百度开源的依存句法分析系统

Extract embedded metadata from HTML markup

a bert for retrieval and generation

Rotary Transformer

速度更快、效果更好的中文新词发现

PyTorch solution of named entity recognition task Using Google AI's pre-trained BERT model.

端到端的长本文摘要模型（法研杯2020司法摘要赛道）

This repository is for the paper "A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check"

PyTorch impelementations of BERT-based Spelling Error Correction Models. 基于BERT的文本纠错模型，使用PyTorch实现。

python | 高效使用统计语言模型kenlm：新词发现、分词、智能纠错等

基于规则的文本纠错系统。

Implementation of a linear-chain CRF in PyTorch

The user manual for Xapian.

在bert4keras下加载CPM_LM模型

Python script to delve into MongoDB's WiredTiger data files