Jiang Junguang's starred repositories
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
awesome-cs-books
🔥 经典编程书籍大全,涵盖:计算机系统与网络、系统架构、算法与数据结构、前端开发、后端开发、移动开发、数据库、测试、项目与团队、程序员职业修炼、求职面试等
PaLM-rlhf-pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
text-to-text-transfer-transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
recommenders
TensorFlow Recommenders is a library for building recommender system models using TensorFlow.
Awesome-RSPapers
Recommender System Papers
fastformers
FastFormers - highly efficient transformer models for NLU
hyperparameter-optimization
Implementation of Bayesian Hyperparameter Optimization of Machine Learning Algorithms
torch-rechub
A Lighting Pytorch Framework for Recommendation Models, Easy-to-use and Easy-to-extend.
BERT-of-Theseus
⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).
SimCSE-Chinese-Pytorch
SimCSE在中文上的复现,有监督+无监督
auto-lambda
The Implementation of "Auto-Lambda: Disentangling Dynamic Task Relationships" [TMLR 2022].
AITM
TensorFlow implementation of Adaptive Information Transfer Multi-task (AITM) framework. Code for the paper accepted by KDD21: Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising. [https://arxiv.org/abs/2105.08489]
taskgrouping
Code for Which Tasks Should Be Learned Together in Multi-task Learning?
Debiased-Self-Training
Code release of paper Debiased Self-Training for Semi-Supervised Learning (NeurIPS 2022 Oral)