Currycurrycurry

Currycurrycurry's Stars

• babysor/MockingBird

  🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

  Language:Python34.9k5.2k

• svc-develop-team/so-vits-svc

  SoftVC VITS Singing Voice Conversion

  Language:Python25.3k4.8k

• apachecn/stanford-game-theory-notes-zh

  📖斯坦福博弈论中文笔记

  Language:Shell18332

• shiokaze/UmamusumeAutoTrainer

  闪耀优俊少女（赛马娘）自动育成工具

  Language:Python23236

• bytedance/byteps

  A high performance and generic framework for distributed DNN training

  Language:Python3.6k488

• tianheyu927/PCGrad

  Code for "Gradient Surgery for Multi-Task Learning"

  Language:Python29935

• wush978/KDD2015wpp

  Reproduce the experiments published in "Predicting Winning Price in Real Time Bidding with Censored Data"

  Language:R4021

• shenweichen/DeepCTR

  Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

  Language:Python7.5k2.2k

• IST-DASLab/gptq

  Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

  Language:Python1.9k150

• intelligent-machine-learning/dlrover

  DLRover: An Automatic Distributed Deep Learning System

  Language:Python1.2k146

• microsoft/DeepSpeed

  DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

  Language:Python34.7k4k

• rahulgaikwad2010/real-time-first-price-auction-machine-learning

  Setting a reserve price induces this by causing bidders to lose at lower bids which encourages higher bidding and more publisher revenue. However, since most of these take place through automated systems, there might be an unknown delay in setting reserve prices & reducing the win rate of bidder & bidder changing their bid shading algorithm & increased publisher revenue.

  Language:Jupyter Notebook72

• zxh0/jvm.go

  A toy JVM written in Go

  Language:Go3.6k470

• chl8856/DeepHit

  DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks

  Language:Python17174

• prajna-lang/prajna

  a program language for AI infrastructure

  Language:C++8312

• data61/MP-SPDZ

  Versatile framework for multi-party computation

  Language:C++896278

• forthespada/CampusShame

  互联网仍有记忆！那些曾经在校招过程中毁过口头offer、意向书、三方的公司！纵然人微言轻，也想尽绵薄之力！

  3.1k151

• chenzomi12/AISystem

  AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

  Language:Jupyter Notebook10.4k1.5k

• intel/intel-extension-for-pytorch

  A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

  Language:Python1.5k236

• WoosukKwon/retraining-free-pruning

  [NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers

  Language:Python16025

• PaddlePaddle/models

  Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

  Language:Python6.9k2.9k

• mit-han-lab/tiny-training

  On-Device Training Under 256KB Memory [NeurIPS'22]

  Language:Python42659

• taizilongxu/interview_python

  关于Python的面试题

  Language:Shell16.5k5.5k

• namhoonlee/snip-public

  SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY

  Language:Python10821

• rk2900/DLF

  Deep learning for flexible market price modeling (landscape forecasting) in real-time bidding advertising. An implementation of our KDD 2019 paper with some other (Python) implemented prediction models.

  Language:Python6916

• google-research/lottery-ticket-hypothesis

  A reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.

  Language:Python706136

• alecwangcq/GraSP

  Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH

  Language:Python9714

• intel/neural-compressor

  SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

  Language:Python2.1k251

• codecaution/Awesome-Mixture-of-Experts-Papers

  A curated reading list of research in Mixture-of-Experts(MoE).

  52040

• Hsword/Hetu

  A high-performance distributed deep learning system targeting large-scale and automated distributed training. If you have any interests, please visit/star/fork https://github.com/PKU-DAIR/Hetu

  Language:Python10145