https://github.com/jancarauma/nanogpt
nanoGPT - A simple GPT-Style Transformer from Scratch in PyTorch
https://github.com/jancarauma/nanogpt
artificial-intelligence attention-mechanism deep-learning gpt language-model language-modeling machine-learning nano-gpt natural-language-processing neural-networks nlp pytorch self-attention text-generation transformer
Last synced: 27 days ago
JSON representation
nanoGPT - A simple GPT-Style Transformer from Scratch in PyTorch
- Host: GitHub
- URL: https://github.com/jancarauma/nanogpt
- Owner: jancarauma
- License: mit
- Created: 2025-06-10T14:25:09.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-06-10T14:26:43.000Z (5 months ago)
- Last Synced: 2025-06-10T16:19:04.234Z (5 months ago)
- Topics: artificial-intelligence, attention-mechanism, deep-learning, gpt, language-model, language-modeling, machine-learning, nano-gpt, natural-language-processing, neural-networks, nlp, pytorch, self-attention, text-generation, transformer
- Language: Python
- Homepage: https://artientista.blogspot.com/2025/06/guia-pratico-aprenda-construir-um.html
- Size: 9.77 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# nanoGPT
A minimalist implementation of a GPT-style transformer model built from scratch using PyTorch.
This project demonstrates the core components of transformer architecture, including multi-head self-attention, positional embeddings, and causal masking, trained on a small custom dataset for simple conversational tasks.
Designed for educational purposes and quick experimentation with language modeling fundamentals.
