luckmoon's repositories
annotated_deep_learning_paper_implementations
🧑🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
awesome-cheatsheets
超级速查表 - 编程语言、框架和开发工具的速查表，单个文件包含一切你需要知道的东西 :zap:
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
blog-example
博客中的示例文件，包含 Kubernetes、Jenkins、Go、Java、SpringBoot、SpringCloud 知识示例等，将结合博客逐步讲解整体的知识内容体系。
BlogShare
Share Materials of my blog
cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
cmake-examples
Useful CMake Examples
cppbestpractices
Collaborative Collection of C++ Best Practices. This online resource is part of Jason Turner's collection of C++ Best Practices resources. See README.md for more information.
Deep-RL-Notes
A collection of comprehensive notes on Deep Reinforcement Learning, customized for UC Berkeley's CS 285 (prev. CS 294-112)
denoising-diffusion-pytorch
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
es_dfm
code of our AAAI 2021 paper Capturing Delayed Feedback in Conversion Rate Prediction via Elapsed-Time Sampling
FastASR
这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 推理模型是基于目前最先进的conformer模型，使用10000+小时的wenetspeech数据集训练得到， 所以识别效果也很好，可以媲美许多商用的ASR软件。
feature-selector
Feature selector is a tool for dimensionality reduction of machine learning datasets
gradnorm_tf
TensorFlow implementation of GradNorm
how-to-optim-algorithm-in-cuda
how to optimize some algorithm in cuda.
llama
Inference code for Llama models
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
PokemonRedExperiments
Playing Pokemon Red with Reinforcement Learning
pytorch-grad-norm
Pytorch implementation of the GradNorm. GradNorm addresses the problem of balancing multiple losses for multi-task learning by learning adjustable weight coefficients.
pytorch-template
Simple project base template for PyTorch deep Learning project. Features clean implementation of DDP training and Hydra config.
Pytorch-Template-1
The template of pytorch trainning and testing
rime-ice
Rime 配置：雾凇拼音 | 长期维护的简体词库
rnn-time-to-event
An approximation of Recurrent Neural Networks to predict the Time to an Event
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
stable-diffusion
A latent text-to-image diffusion model
the-art-of-command-line
Master the command line, in one page
tianshou
An elegant PyTorch deep reinforcement learning library.
toyML
Toy Machine Learning Package
uc-berkeley-cs285-drl-chinese
A Chinese version textbook of UC Berkeley CS285 Deep Reinforcement Learning 2021 fall, taught by Prof. Sergey Levine. 伯克利大学 CS285 深度强化学习 2021 秋季课程的个人中文译本.
word2vec_commented
Commented (but unaltered) version of original word2vec C implementation.