Stars
🤗 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。
PyMongo - the Official MongoDB Python driver
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
Extract embedded metadata from HTML markup
PyTorch solution of named entity recognition task Using Google AI's pre-trained BERT model.
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
Implementation of a linear-chain CRF in PyTorch
Python script to delve into MongoDB's WiredTiger data files