ChewKokWah

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

haystack

:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

dgl

Python package built to ease deep learning on graph, on top of existing DL frameworks.

detr

End-to-End Object Detection with Transformers

deit

Official DeiT repository

ResNeSt

ResNeSt: Split-Attention Networks

ranking

Learning to Rank in TensorFlow

annotated_research_papers

This repo contains annotated research papers that I found really good and useful

Smart_Construction

Base on YOLOv5 Head Person Helmet Detection on Construction Sites，基于目标检测工地安全帽和禁入危险区域识别系统，🚀😆附 YOLOv5 训练自己的数据集超详细教程🚀😆2021.3新增可视化界面❗❗

TextBrewer

A PyTorch-based knowledge distillation toolkit for natural language processing

TikZ

Complete collection of my PGF/TikZ figures.

imagenette

A smaller subset of 10 easily classified classes from Imagenet, and a little more French

maxas

Assembler for NVIDIA Maxwell architecture

multiwoz

Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)

bookcorpus

Crawl BookCorpus

bigbird

Transformers for Longer Sequences

indonlu

The first-ever vast natural language processing benchmark for Indonesian Language. We provide multiple downstream tasks, pre-trained IndoBERT models, and a starter code! (AACL-IJCNLP 2020)

PaddleFleetX

飞桨大模型开发套件，提供大语言模型、跨模态大模型、生物计算大模型等领域的全流程开发工具链。

convai

electra_pytorch

Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)

DRCD

A 30000+ Chinese MRC dataset - Delta Reading Comprehension Dataset

efficient-attention

An implementation of the efficient attention module.

knowledge-net

KnowledgeNet: A Benchmark Dataset for Knowledge Base Population

Chinese-RC-Datasets

Collections of Chinese reading comprehension datasets

layer-to-layer-pytorch

PyTorch implementation of L2L execution algorithm

LogiQA-dataset

BMCNNwHFCs

The code for "No Routing Needed Between Capsules". This repository contains the code used for the experiments detailed in a forthcoming paper. The paper is available pre-published at arXiv: http://arxiv.org/abs/2001.09136

translucent-answer-prediction

TAP (Translucent Answer Prediction), is a system to identify answers and evidence (in the form of supporting facts) in an RCQA task that requires multi-hop reasoning. TAP comprises two loosely coupled networks, called Local and Global Interaction eXtractor (LoGIX) and the Answer Predictor (AP).

hugdatafast

The elegant integration of huggingface/nlp and fastai2 and handy transforms using pure huggingface/nlp