#From-scratch
Showing 19 of 19 repositories tagged #from-scratch, ranked by stars
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Learn it. Build it. Ship it for others.
Build a modern LLM from scratch. Every line commented. Explained like we are five.
Pure Rust implementation of a minimal Generative Pretrained Transformer
Agent工程师最全学习路径 · 从零精通 AI 工程 · 20 阶段 503 课 · 中文全量翻译 + 配套站点 + 动画讲解视频 · 如何成为 AI Agent 工程师的修成指南
A x86_64 C99 compiler written in Rust from scratch
An OS which is all about learning!
ncurses 3d object viewer
A complete neural network built entirely in x86 assembly language that learns to recognize handwritten digits from the MNIST dataset. No frameworks, no high-level languages - just pure assembly - ~5.3× faster than NumPy
This code is part of my post on Medium.
A web browser written from scratch — a platform-agnostic Rust engine (networking, HTML/CSS parsing, DOM, style, layout, paint) with a thin native app shell per OS.
逐行对照 MiniMind 源码精读、并延伸到大模型技术体系的中文学习笔记 —— 预训练 / SFT / DPO / PPO / GRPO、训练机制、MiniMind2→3 版本对照、真实实验证据。
从零搭建大模型知识库(Build LLM RAG Corpus from scratch)
A simple database built from scratch in Rust
GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.
Build a transformer model from scratch using pytorch to understand its inner workings and gain hands-on experience with deep learning models in PyTorch.
Build a Neural Network from scratch in C++ to deeply understand how it works, not just how to use it.
Build a GPT from scratch, one concept at a time, from pure Python to PyTorch, JAX, MLX, and production serving. Inspired by Andrej Karpathy's microGPT.
Deep Neural Network from scratch in C++ for learning purposes