liuxiaoqun Goto Github PK

ark-nlp

A private nlp coding package, which quickly implements the SOTA solutions.

beir

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

bert

a simple yet complete implementation of the popular BERT model

bert-gec

bertwithpretrained

基于PyTorch框架实现的BERT模型及其相关下游微调任务

chatgpt_academic

科研工作专用ChatGPT拓展，特别优化学术Paper润色体验，支持自定义快捷按钮，支持markdown表格显示，Tex公式双显示，代码显示功能完善，新增本地Python工程剖析功能/自我剖析功能

chinese-llama-alpaca

中文LLaMA&Alpaca大语言模型+本地部署 (Chinese LLaMA & Alpaca LLMs)

deepctr

deeplearning-models

A collection of various deep learning architectures, models, and tips

deepspeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

dit

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

dssm

DSSM and Multi-View DSSM

dssm-lookalike

flink-recommandsystem-demo

:helicopter::rocket:基于Flink实现的商品实时推荐系统。flink统计商品热度，放入redis缓存，分析日志信息，将画像标签和实时记录放入Hbase。在用户发起推荐请求后，根据用户画像重排序热度榜，并结合协同过滤和标签两个推荐模块为新生成的榜单的每一个产品添加关联产品，最后返回新的用户列表。

hacked_earnings_jfe

Code and data for Price Revelation from Insider Trading: Evidence from Hacked Earnings News

harvesttext

文本挖掘和预处理工具（文本清洗、新词发现、情感分析、实体识别链接、关键词抽取、知识抽取、句法分析等），无监督或弱监督方法

hit-cosem-2017

Computational Semantics 2017 / Wanxiang Che, HIT

keybert

Minimal keyword extraction with BERT

keyword-extractor

关键词抽取项目

luke

LUKE -- Language Understanding with Knowledge-based Embeddings

mingpt

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

ml-nlp

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

nlp-competitions-list-review

复盘所有NLP比赛的TOP方案，只关注NLP比赛，持续更新中！

nlp_paper_study

该仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记

nlpdemo

NLP方面的一些小的demo,包括文本生成,文本分类,文本聚类等等,使用tensorflow实现,长期更新,欢迎指正,交流

papersreimplementations

Personal short implementations of Machine Learning papers

searchingsystem

python实现的基于倒排索引和向量空间模型实现的信息检索系统

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

siamese_dssm

siamese dssm sentence_similarity sentece_similarity_rank tensorflow

smt

Statistical Machine Translation implementation with Python: especially IBM Model1, 2, and phrase-based machine translation.