Stars
FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。
Source code for Twitter's Recommendation Algorithm
Video+code lecture on building nanoGPT from scratch
Official Repository for SIGIR2024 Demo Paper "An Integrated Data Processing Framework for Pretraining Foundation Models"
🚁🚀基于Flink实现的商品实时推荐系统。flink统计商品热度，放入redis缓存，分析日志信息，将画像标签和实时记录放入Hbase。在用户发起推荐请求后，根据用户画像重排序热度榜，并结合协同过滤和标签两个推荐模块为新生成的榜单的每一个产品添加关联产品，最后返回新的用户列表。
Apache DolphinScheduler is the modern data orchestration platform. Agile to create high performance workflow with low-code
Single-file pytorch implementation of hybrid-SAC
This code contains all code developed to analyze early-exit DNNs considering an edge-cloud architecture.
Learning materials of Transformer, including my code, XMind, PDF and so on
CTR prediction model based on spark(LR, GBDT, DNN)
笔者在网上查找一些过来人面试推荐算法岗位的经验时，常常感到翻阅多篇帖子看起来不太方便，于是萌生了整理一系列面试题目的想法。能够方便自己平时自己进行查找，也方便各位找实习和找工作的同学复习和备战面试！
Foreign language reading and translation assistant based on copy and translate.
Pytorch implementation of channel pruning and AMC
My DRL library with tensorflow1.14 based on openai spinning-up
PyTorch implementation of Alexnet with an early exit structure as defined by S. Teerapittayanon et al. Model is designed for and trained on CIFAR-10, reaching ~80% accuracy.
Latex code for making neural networks diagrams
基于提前退出部分样本原理而实现的带分支网络（supported by chainer）
This project will realize experiments about BranchyNet partitioning using pytorch framework
Memory consumption and FLOP count estimates for convnets
[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices