Starred repositories
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Elephant activation function is a novel class of activation functions designed to enhance the resilience of neural networks to catastrophic forgetting.
A feature-rich command-line audio/video downloader
Optim4RL is a Jax framework of learning to optimize for reinforcement learning.
The official code release for Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo, ICLR 2024.
Jaxplorer is a Jax reinforcement learning (RL) framework for exploring new ideas.
An open source library and framework for deep learning on satellite and aerial imagery.
You like pytorch? You like micrograd? You love tinygrad! ❤️
A Python toolbox for performing gradient-free optimization
Submissions for the Coursera specilization Modern Robotics: Mechanics, Planning, and Control Specialization
4
Updated Jul 2, 2023
Infinite Photorealistic Worlds using Procedural Generation
A customisable 3D platform for agent-based AI research
Enable Bing ChatGPT on Chrome and Firefox
Welcome to the Awesome Feature Learning in Deep Learning Thoery Reading Group! This repository serves as a collaborative platform for scholars, enthusiasts, and anyone interested in delving into th…
Machine (mainly reinforcement) learning algorithms using JAX
The official implementation of Memory-efficient DQN algorithm.
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
Automation scripts for setting up a basic development environment.
Let ChatGPT truly learn how to go online and call APIs! 'EX-ChatGPT' can rival and even surpass NewBing
A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...
From search engines, to science, to robotics, this reposity is meant to showcase the use of reinforcement learning in the world..
《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀
This project is deprecated. Check my new project ChatHub:
经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新
Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagation
An efficient remote-onboard architecture for real-time Reinforcement Learning