Stars
✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】
Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)
awesome papers in LLM interpretability
A playbook for systematically maximizing the performance of deep learning models.
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
异步图书：《 GPT图解 大模型是怎样构建的》- 这套代码是AI Coder出现之前，自己用纯手工搭建的一套简单有效的NLP经典算法集合。在大语言模型推动的AI Coder兴起之后，很少有机会再创作这么有“手工风”的代码了，不知道这是值得开心还是值得遗憾的事情。
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/
A local chatbot fine-tuned by bilibili user comments.
official code for "Large Language Models as Optimizers"
ETH Zürich Deep Learning in Scientific Computing Master's course 2023
The Python library to create stand-alone and interactive d3 charts.
Matplotlib styles for scientific plotting
Series of notebooks to illustrate different plotting features using Python
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Awesome-LLM: a curated list of Large Language Model
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Transfer learning in deep reinforcement learning for continuous control. Implemented DDPG and TD3 algorithms and evaluated ability to adapt to changes in environment dynamics and new environments
Implementation of Deep Deterministic Policy Gradient (DDPG) with Prioritized Experience Replay (PER)
A curated list of awesome exploration RL resources (continually updated)
Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://arxiv.org/abs/2305.18499
An elegant PyTorch offline reinforcement learning library for researchers.