Shypd.aiThe largest open index of AI toolsreasoning-from-scratch is an Open Source & Models tool that provides code and resources for implementing a reasoning LLM in PyTorch from scratch. It serves as the official code repository for the book *Build a Reasoning Model (From Scratch)*, helping users understand how reasoning large language models work.
Trending
Also listed in
About
reasoning-from-scratch is the official code repository for the book *Build a Reasoning Model (From Scratch)*, offering a hands-on approach to understanding and implementing reasoning large language models (LLMs) in PyTorch. Users start with a pre-trained base LLM and progressively add reasoning capabilities, mirroring approaches used in large-scale models like DeepSeek R1 and GPT-5 Thinking. The repository includes code for generating text, evaluating reasoning models, improving reasoning with inference-time scaling and self-refinement, and training models with reinforcement learning. It also covers distilling reasoning models for efficiency and provides bonus materials on topics like GPU optimization, advanced evaluation methods, and building chat interfaces. The code is designed to run on consumer hardware, with GPU utilization if available, making it accessible for a wide audience.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
