CSerxy

IDPG

IDPG: An Instance-Dependent Prompt Generation Method

IdentifyShifts

The official implementation of the SIGIR'18 paper "Identify Shifts of Word Semantics through Bayesian Surprise"

domainShiftVisualization

lazy to use scp

simclr

SimCLR - A Simple Framework for Contrastive Learning of Visual Representations

TensorFlow-Course

Simple and ready-to-use tutorials for TensorFlow

545-final-project-FS-implementation

This is the implementation of 4 tradition feature selection algorithms and 6 SSFS methods.

ALBERT

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

attentions

PyTorch implementation of some attentions for Deep Learning Researchers.

bert

TensorFlow code and pre-trained models for BERT

CERT

comp-gap-public

cserxy.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

DeepLearing-Interview-Awesome-2024

We'll cover some of the most common Deep Learning Interview Questions and answers and provide detailed answers to help you

DeepLearningExamples

Deep Learning Examples

DiffCSE

Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"

electra

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

examples

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

FastChat

An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.

flash-attention

Fast and memory-efficient exact attention

grade-school-math

hexo

A fast, simple & powerful blog framework, powered by Node.js.

LaTeX-Drawing

LaTeX Drawing

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。

my_vim_environment

Every time it takes me long to build a new vim environment on a new machine. Decided to put my .vimrc and corresponding operations here to save my time in the future.

QuestionDecomposition

SimCSE

EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings

SpanBERT

Code for using and evaluating SpanBERT.

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Universal-Prompt-Injection

The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".