rasbt/LLMs-from-scratchπ₯ active
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
$ git clone https://github.com/stochasticai/xTuring.gitImplement a ChatGPT-like LLM in PyTorch from scratch, step by step
π Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
γε€§θ―θ¨ζ¨‘εγδ½θ οΌθ΅΅ι«οΌζεζ― οΌε¨ζοΌε倩δΈοΌζη»§θ£
Build a modern LLM from scratch. Every line commented. Explained like we are five.
Data from GitHub Β· snapshot Sep 24, 2026