This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

This repo demonstrates exposing LangGraph workflow using FastAPI to a front end like Streamlit and more

Streamlit and LangGraph Intersection Starters, LangGraph with Streamlit, Streamlit with LangGraph

Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit

Fully open reproduction of DeepSeek-R1

MovieLens based recommender system.使用MovieLens数据集训练的电影推荐系统。

A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

xgboost Extension for Easy Ranking & TreeFeature

[NAACL 2021] A Frustratingly Easy Approach for Entity and Relation Extraction https://arxiv.org/abs/2010.12812

The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.

full scratch GBrank (Z. Zhang, 2007)

PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.

北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

Bert源码阅读与讲解(Pytorch版本)-以BERT文本分类代码为例子

Chinese NER using Lattice LSTM. Code for ACL 2018 paper.

预训练语言模型综述

总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力

总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力

缠中说禅技术分析工具；缠论；股票；期货；Quant；量化交易

搜索所有中文NLP数据集，附常用英文NLP数据集

A more complete example of programming with PDFMiner, which continues where the default documentation stops

Sohu 2017 competition. We won the third prize.

paper note, including personal comments, introduction, code etc

The Research Spider for Anthology. This toolkit can automatically grab the papers information by given keywords in title. You can set the search params: the conference, publication date and the key…

Sentence Distance

🚀CNN-based image retrieval built on Keras

NLP上手教程