as837430732

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

PlotNeuralNet

Latex code for making neural networks diagrams

download

Lantern官方版本下载 蓝灯 翻墙 代理 科学上网 外网 加速器 梯子 路由 proxy vpn circumvention gfw

gpt-3

GPT-3: Language Models are Few-Shot Learners

hexo-theme-butterfly

🦋 A Hexo Theme: Butterfly

pytorch-cifar

95.47% on CIFAR10 with PyTorch

bert4keras

keras implement of transformers for humans

nlpaug

Data augmentation for NLP

TextAttack

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

roberta_zh

RoBERTa中文预训练模型: RoBERTa for Chinese

adversarial-attacks-pytorch

PyTorch implementation of adversarial attacks [torchattacks]

FALdetector

Code for the paper: Detecting Photoshopped Faces by Scripting Photoshop

TextGAN-PyTorch

TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.

dive-into-cv-pytorch

动手学CV-Pytorch版

Integrated-Gradients

Attributing predictions made by the Inception network using the Integrated Gradients method

switch-cuda

A simple bash script for switching between installed versions of CUDA.

pytorch-MNIST-CelebA-GAN-DCGAN

Pytorch implementation of Generative Adversarial Networks (GAN) and Deep Convolutional Generative Adversarial Networks (DCGAN) for MNIST and CelebA datasets

BERT-SQuAD

SQuAD Question Answering Using BERT, PyTorch

Pytorch-Camp

TransferAttack

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

awesome-llm-attributions

A Survey of Attributions for Large Language Models

sentiment_dataset

Sentiment_Analysis_Imdb

Using Bert/Roberta + LSTM/GRU/BiLSTM/TextCNN to do the sentiment analysis on the imdb datasets.

AdvDrop

Code for "Adversarial attack by dropping information." (ICCV 2021)

cs224n_2019

cs224n 2019 Note & Assignment Code

ELA

ELA 全称：Error Level Analysis ，汉译为“错误级别分析”或者叫“误差分析”。通过检测特定压缩比率重新绘制图像后造成的误差分布，可用于识别JPEG图像的压缩。

APT

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

perturbations-in-the-wild

Repository of the paper "Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense", ACL22 (Findings)

CoT_distillation

基于Chatglm的思维链蒸馏

Text-classification

Some common text classification models