ryh95

Prompt-Engineering-Guide

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

DeepSpeed

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

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

jina

☁️ Build multimodal AI applications with cloud-native stack

Megatron-LM

Ongoing research training transformer models at scale

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

aima-python

Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

LaWGPT

🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

Stanford-CS-229

A Chinese Translation of Stanford CS229 notes 斯坦福机器学习CS229课程讲义的中文翻译

DPR

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

cs229-2018-autumn

All notes and materials for the CS229: Machine Learning course by Stanford University

TAADpapers

Must-read Papers on Textual Adversarial Attack and Defense

key-book

《机器学习理论导引》（宝箱书）的证明、案例、概念补充与参考文献讲解。

parser

:rocket: State-of-the-art parsers for natural language.

OpenAttack

An Open-Source Package for Textual Adversarial Attack.

textflint

Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing

BMInf

Efficient Inference for Big Models

LMaaS-Papers

Awesome papers on Language-Model-as-a-Service (LMaaS)

hotpot

high_performance_python_2e

Code for the book "High Performance Python 2e" by Micha Gorelick and Ian Ozsvald with OReilly

golden-retriever

Authors' implementation of EMNLP-IJCNLP 2019 paper "Answering Complex Open-domain Questions Through Iterative Query Generation"

emdr2

Code and Models for the paper "End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering" (NeurIPS 2021)

hearst_patterns_python

This is an implementation of Hearst patterns, for finding hyponyms, written in Python.

Distributional-Generalization-in-Natural-Language-Processing

Distributional Generalization in NLP. A roadmap.

crfpar

[ACL'20, IJCAI'20] Code for "Efficient Second-Order TreeCRF for Neural Dependency Parsing" and "Fast and Accurate Neural CRF Constituency Parsing".

jina-financial-qa-search

rainier

adversarial-training-survey

Papers, sites and slides for Adversarial Training