gongwu

DESCN

Implementation of paper DESCN, which is accepted in SIGKDD 2022.

LLM101n

LLM101n: Let's build a Storyteller

dive-into-llms

《动手学大模型Dive into LLMs》系列编程实践教程

EasyRec

A framework for large scale recommendation algorithms.

onerec

在常规推荐系统算法和系统双优化的范式下，一线公司针对单个任务或单个业务的效果挖掘几乎达到极限。从2019年我们开始关注多种信息的萃取融合，提出了OneRec算法，希望通过平台或外部各种各样的信息来进行知识集成，打破数据孤岛，极大扩充推荐的“Extra World Knowledge”。 已实践的算法包括行为数据，内容描述，社交信息，知识图谱等。在OneRec，每种信息和整体算法的集成是可插拔的，这样的话一方面方便大家在自己的平台数据下灵活组合各种信息，另一方面方便开源共建，大家可以在上边集成自己的各种算法。今天分享的都是之前在线上验证过效果的工作，相关代码和论文已经开源在：。欢迎大家开源共建。

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

grok-1

Grok open release

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

mPLUG-Owl

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

DeepSpeed

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

DeepSpeedExamples

Example models using DeepSpeed

GPT-4-LLM

Instruction Tuning with GPT-4

alpaca-lora

Instruct-tune LLaMA on consumer hardware

causalml

Uplift modeling and causal inference with machine learning algorithms

kaggle-predict-future-sales

Kaggle's Predict Future Sales competition project (TOP 15 solution as of March 2020)

PyTorch-On-Angel

PyTorch On Angel, arming PyTorch with a powerful Parameter Server, which enable PyTorch to train very big models.

RSPapers

A Curated List of Must-read Papers on Recommender System.

nndl.github.io

《神经网络与深度学习》 邱锡鹏著 Neural Network and Deep Learning

Dialogue

texar

Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/

nlg-eval

Evaluation code for various unsupervised automated metrics for Natural Language Generation.

HybridNCM

Code on A Hybrid Retrieval-Generation Neural Conversation Model (CIKM 2019)

IMN

CIKM 2019: Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots

models

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

AnyQ

FAQ-based Question Answering System

data2text-entity-py

Code for ACL 2019 paper on Data-to-text Generation with Entity Modeling

TG-Reading-List

A text generation reading list maintained by Tsinghua Natural Language Processing Group.

Skeleton-Based-Generation-Model

Code for "A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation" (EMNLP 2018)

HRAN