syw1996

golden-horse

Named Entity Recognition for Chinese social media (Weibo). From EMNLP 2015 paper.

TableGPT

Flat-Lattice-Transformer

code for ACL 2020 paper: FLAT: Chinese NER Using Flat-Lattice Transformer

BERT-NER-Pytorch

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

DeepCTR

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

ranking

Learning to Rank in TensorFlow

DeepCTR-Torch

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

RecommenderSystems

feast

The Open Source Feature Store for Machine Learning

ngender

根据姓名来判断性别

CSN-SAPR

Translation_Spark-The-Definitive-Guide

Translation of the book,"Spark-The-Definitive-Guide", from English into Chinese. 书籍 《Spark权威指南》翻译

SimCSE

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

faiss

A library for efficient similarity search and clustering of dense vectors.

promptsource

Toolkit for creating, sharing and using natural language prompts.

OpenPrompt

An Open-Source Framework for Prompt-Learning.

Knover

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

loss_dropper

CommentGeneration

Code for lyric-section-to-comment generation based on huggingface transformers.

UER-py

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

clip-as-service

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

poetry

汉语现代诗歌语料库整理，3489诗人，81.7K诗歌，15.43M字。持续扩充...

ETM

Topic Modeling in Embedding Spaces

Chinese-Punctuation-Restoration-with-Bert-CNN-RNN

A Bert-CNN-LSTM model for punctuation restoration

kenlm

KenLM: Faster and Smaller Language Model Queries

datasketch

MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW

ltp

Language Technology Platform

onnx

Open standard for machine learning interoperability

Megatron-LM

Ongoing research training transformer models at scale

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support