Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.
-
Updated
Jan 12, 2024 - JavaScript
#
nanogpt
Here are 153 public repositories matching this topic...
This repository contains the collection of explorative notebooks pure in python and in the language that we, humans can read. Have tried to compile all lectures from the Andrej Karpathy's 💎 playlist on Neural Networks - which we will end up with building GPT.
deep-learning neural-network tokenizer pytorch transformer gpt nlg pytorch-tutorial educational-project andrej-karpathy pytorch-implementation zero-to-mastery neural-network-from-scratch zero-to-hero nanogpt gpt-from-scratch
-
Updated
Apr 30, 2024 - Jupyter Notebook
Symbolic Music NLP Artificial Intelligence Toolkit
music nlp raspberry-pi deep-learning midi artificial-intelligence music-generation computer-music plagiarism-detection midi-toolkit architectures markovify midi-processing artificial-intelligence-systems midi-processor midi-search midi-classification symbolic-music music-origami nanogpt
-
Updated
Aug 20, 2026 - Jupyter Notebook
LLM frontend for roleplay
cli terminal storytelling tui interactive-fiction roleplay mlx creative-writing llm nanogpt llamacpp local-llm sillytavern koboldcpp openrouter ollama lmstudio ai-roleplay sillytavern-alternative
-
Updated
Sep 8, 2026 - Python
A GPT built and trained in 243 lines of pure, dependency-free Python - no PyTorch, no NumPy. Based on Andrej Karpathy's microgpt, it hand-rolls autograd, attention and Adam to show how little a language model really needs.
python machine-learning deep-learning autograd transformer neural-networks educational minimalist gpt language-model attention-mechanism from-scratch karpathy micrograd llm nanogpt
-
Updated
Feb 12, 2026 - Python
burn inference and training of dragon models 🔥🐉
-
Updated
Apr 12, 2026 - Rust
A compact, readable PyTorch reference implementation of the DeepSeek-V4 architecture (Flash and Pro), in the spirit of nanoGPT. ~4,300 LOC.
pytorch transformer moe reference-implementation mixture-of-experts sparse-attention llm nanogpt deepseek deepseek-v4
-
Updated
Aug 14, 2026 - Python
Code repository for the paper "Traveling Words: A Geometric Interpretation of Transformers"
-
Updated
Dec 20, 2023 - Python
Production-Level Large Language Model Training & Deployment Framework
deep-neural-networks deep-learning gemini gpt large-language-models llm chatgpt nanogpt qwen deepseek personalgpt
-
Updated
Jul 12, 2026 - Python
This repo represents my Nano-GPT speedrun playground, which started coding along Let's reproduce GPT-2 (124M), then moved into further improvements.
decoder transformers speedrun muon rope gpt-2 gpt3 decoder-model nanogpt flexattention flashattention
-
Updated
Aug 12, 2026 - Python
A secure multi-provider, multimodal Discord AI room harness for NanoGPT, OpenAI, Anthropic, xAI, and Gemini.
discord-bot artificial-intelligence gemini openai grok codex multi-provider multimodal nanogpt elevenlabs anthropic
-
Updated
Aug 27, 2026 - JavaScript
The simplest masked-diffusion language model you can actually train, debug, and learn from — ~1100 lines of plain PyTorch, char-level, with an honest head-to-head against a matched autoregressive baseline. Watch text crystallize from noise.
-
Updated
May 16, 2026 - Python
A 134M-parameter GPT written from scratch in PyTorch, no nn.Transformer and no HuggingFace, pretrained on a 7B tokens corpus of FineWeb-Edu, where it consumed 1.2B tokens on one free Kaggle P100. Held-out perplexity 36.12 against a Chinchilla prediction of 38.70.
machine-learning deep-learning reproducible-research pytorch transformer gpt language-model from-scratch perplexity ml-engineering pretraining llm nanogpt fineweb
-
Updated
Sep 6, 2026 - Jupyter Notebook
Corso web gratuito in italiano, con repository open source, per costruire da zero un modello GPT decoder-only in PyTorch in 42 lezioni con spiegazioni, matematica, codice eseguibile e snapshot progressivi.
education machine-learning deep-learning text-generation pytorch transformer gpt mps language-model tokenization multi-head-attention gradient-accumulation checkpointing apple-silicon llm nanogpt decoder-only-transformer fineweb-edu gpt-2-bpe causal-self-attention
-
Updated
Sep 9, 2026 - Python
Fast multi-instrumental music transformer with 4k sequence length, pentagram full-range MIDI notes encoding, notes counters and outro tokens
music midi artificial-intelligence midi-api music-generation pentagram midi-encoder music-transformer music-ai nanogpt
-
Updated
Oct 17, 2023 - Python
Add this topic to your repo
To associate your repository with the nanogpt topic, visit your repo's landing page and select "manage topics."