LLMs From Scratch
Build a ChatGPT-like LLM in PyTorch step by step
Train a tiny language model from scratch on regular hardware
MiniMind is a PyTorch codebase for training a tiny 64M-parameter language model from scratch on ordinary hardware. It is aimed at learners and developers who want to understand pretraining, fine-tuning, LoRA, and DPO without a large compute budget.
Provides a complete training recipe with pretraining, supervised fine-tuning, LoRA, and DPO stages written in readable PyTorch so users can run and modify each step.
Top 10 Repos explained: Archify, Omarchi, OpenMAIC, and more
Build a ChatGPT-like LLM in PyTorch step by step
Tiny special-purpose models that run locally on everyday devices
A pretend trading firm staffed entirely by AI agents
Multi-agent coding teams with roles, models and memory
LLM-powered multi-market stock analysis with dashboards and alerts
Browse real system prompts from major AI products