LLMs-from-scratch and train-llm-from-scratch
These are competitors offering alternative pedagogical approaches to the same goal: the first provides a comprehensive, step-by-step implementation guide emphasizing architectural understanding, while the second offers a more streamlined, end-to-end training pipeline prioritizing practical results.
About LLMs-from-scratch
rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
This project provides the practical code and guidance to build your own custom GPT-like large language model (LLM) from the ground up. You'll learn how to take raw text data, process it, and train a functional LLM that can generate text or follow instructions. This is designed for AI practitioners, machine learning engineers, and researchers who want to deeply understand and implement LLMs.
About train-llm-from-scratch
FareedKhan-dev/train-llm-from-scratch
A straightforward method for training your LLM, from downloading data to generating text.
This project offers a clear path to building your own custom large language model (LLM). You provide a large dataset of text, and the system trains a language model that can then generate new, coherent text based on what it learned. This is for AI researchers, hobbyists, or developers who want to experiment with creating their own text-generating AI.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work