rasbt/reasoning-from-scratchGitHub
The same from-scratch teaching style but centered on reasoning LLMs (RL/GRPO), if you want that focus.
Implement a reasoning LLM in PyTorch from scratch, step by step
- 5.3k
- Jupyter Notebook
- Apache-2.0
active24d ago
rasbt/LLMs-from-scratch Alternatives
LLM from scratch education
A step-by-step educational repository that implements a ChatGPT-like LLM in PyTorch from scratch, including pretraining and finetuning.
Drop-in peers
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
raiyanyahya/how-to-train-your-gptGitHub
A more heavily commented, beginner-friendly GPT from-scratch with an MIT license.
Build a modern LLM from scratch. Every line commented. Explained like we are five.
- 3.4k
- Jupyter Notebook
- MIT
active1mo ago
jingyaogong/minimindGitHub
A minimal Apache-2.0 64M LLM from scratch that trains in hours, for a quick simple codebase.
🧠 Train a 64M-parameter LLM from scratch in just 2h!
- 61.7k
- Python
- Apache-2.0
active24d ago
Same job, different approach
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
mlabonne/llm-courseGitHub
A structured LLM course with Colab notebooks, for learners who prefer a curated roadmap over a single book codebase.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
- 83.0k
- Apache-2.0
slowing8mo ago
HandsOnLLM/Hands-On-Large-Language-ModelsGitHub
An applied book that focuses on using and fine-tuning existing LLMs, for a hands-on rather than from-scratch approach.
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
- 29.2k
- Jupyter Notebook
- Apache-2.0
active6mo ago
Listed as an alternative to
These projects were analysed and named LLMs-from-scratch among their alternatives. The relationship is not symmetric — how LLMs-from-scratch rates them is a separate judgement, made when LLMs-from-scratch is analysed in its own right.
FareedKhan-dev/train-llm-from-scratchGitHub
calls LLMs-from-scratch “Choose this for a broader, continuously updated textbook-style from-scratch LLM implementation.”
A straightforward method for training your LLM, from downloading data to generating text.
9.4kPythonactive
fengdu78/Coursera-ML-AndrewNg-NotesGitHub
calls LLMs-from-scratch “Choose this when you want a step-by-step PyTorch implementation guide for LLMs.”
吴恩达老师的机器学习课程个人笔记
37.8kHTMLslowing
HandsOnLLM/Hands-On-Large-Language-ModelsGitHub
calls LLMs-from-scratch “If you want to understand LLM internals by implementing a ChatGPT-like model from scratch in PyTorch.”
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
29.2kJupyter Notebookactive
mlabonne/llm-courseGitHub
calls LLMs-from-scratch “Narrower implementation of a GPT-like model step-by-step; choose for code-level understanding.”
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
83.0kslowing
ShusenTang/Dive-into-DL-PyTorchGitHub
calls LLMs-from-scratch “choose for code-first implementation of GPT-like LLMs in PyTorch, but it is much narrower than D2L's breadth”
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
19.5kJupyter Notebookdormant