rasbt/LLMs-from-scratchGitHub
calls how-to-train-your-gpt “A more heavily commented, beginner-friendly GPT from-scratch with an MIT license.”
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
105.3kJupyter Notebookactive
raiyanyahya/how-to-train-your-gpt Alternatives
how-to-train-your-gpt is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
Listed as an alternative to
These projects were analysed and named how-to-train-your-gpt among their alternatives. The relationship is not symmetric — how how-to-train-your-gpt rates them is a separate judgement, made when how-to-train-your-gpt is analysed in its own right.
jingyaogong/minimindGitHub
calls how-to-train-your-gpt “Choose this if you want an extremely beginner-friendly, fully commented from-scratch GPT with an MIT license.”
🧠 Train a 64M-parameter LLM from scratch in just 2h!
61.7kPythonactive
FareedKhan-dev/train-llm-from-scratchGitHub
calls how-to-train-your-gpt “Choose it if you want an ultra-commented, beginner-oriented from-scratch GPT implementation.”
A straightforward method for training your LLM, from downloading data to generating text.
9.4kPythonactive
mlabonne/llm-courseGitHub
calls how-to-train-your-gpt “Narrow from-scratch GPT build with line-by-line explanations; choose for beginner-friendly code walkthrough.”
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
83.0kslowing
graykode/nlp-tutorialGitHub
calls how-to-train-your-gpt “Choose for a single-model deep dive into building a GPT/LLM from scratch; narrower but very detailed.”
Natural Language Processing Tutorial for Deep Learning Researchers
14.9kJupyter Notebookdormant