examples

Source

  • Source kind: github-repository
  • URL: https://github.com/karpathy/examples
  • Discovery source: https://github.com/karpathy/examples
  • License: BSD-3-Clause
  • Distribution policy: public-summary-plus-license-aware-excerpts
  • Public mirror status: partial excerpt
  • Content hash: 6627a7d10ce1270d512f57bdc48f8a81a6bcd72610b6338d7b5a12be8298a448
  • First seen: 2026-05-15
  • Last changed: 2026-05-15

Classification

Summary

PyTorch Examples A repository showcasing examples of using $1 - MNIST Convnets - Word level Language Modeling using LSTM RNNs - Training Imagenet Classifiers with Residual Networks - Generative Adversarial Networks (DCGAN) - Variational Auto-Encoders - Superresolution using an efficient sub-pixel convolutional neural network - Hogwild training of shared ConvNets across multiple processes on MNIST - Training a CartPole to balance in OpenAI Gym with actor-critic - Natural Language Inference (SNLI) with GloVe vectors, LSTMs, and torchtext - Time sequence prediction - create an LSTM to learn Sine waves Additionally,…

What This Teaches

  • How modern LLM training or inference can be reduced to compact, inspectable systems.
  • Useful as a reference for building mental models of GPT-style models without hiding behind framework scale.

Why It Matters

This is high-priority for Vipin because it connects directly to LLM systems, evaluation, and research implementation judgment.

Repository Snapshot

  • Full name: karpathy/examples
  • Default branch: master
  • HEAD: f9820471d615d848c14661b2d582417ca3aee8a3
  • Stars at crawl: 136
  • Forks at crawl: 44
  • File count: 65
  • README path: README.md
  • License path: LICENSE
  • Created: 2018-05-16T20:45:57Z
  • Updated: 2026-04-23T13:20:55Z
  • Pushed: 2018-05-15T08:25:43Z

Top-Level Structure

  • fast_neural_style: 17
  • word_language_model: 10
  • super_resolution: 6
  • reinforcement_learning: 4
  • snli: 4
  • vae: 4
  • [root]: 3
  • dcgan: 3
  • imagenet: 3
  • mnist: 3
  • mnist_hogwild: 3
  • time_sequence_prediction: 3

File Extension Profile

  • .py: 28
  • .md: 11
  • .txt: 11
  • .jpg: 10
  • .gitignore: 2
  • [none]: 2
  • .sh: 1

Tags / Release-Like Markers

  • No git tags found in the shallow local clone.

Sample File Tree

  • .gitignore
  • dcgan/main.py
  • dcgan/README.md
  • dcgan/requirements.txt
  • fast_neural_style/download_saved_models.sh
  • fast_neural_style/images/content-images/amber.jpg
  • fast_neural_style/images/output-images/amber-candy.jpg
  • fast_neural_style/images/output-images/amber-mosaic.jpg
  • fast_neural_style/images/output-images/amber-rain-princess.jpg
  • fast_neural_style/images/output-images/amber-udnie.jpg
  • fast_neural_style/images/style-images/candy.jpg
  • fast_neural_style/images/style-images/mosaic.jpg
  • fast_neural_style/images/style-images/rain-princess.jpg
  • fast_neural_style/images/style-images/rain-princess-cropped.jpg
  • fast_neural_style/images/style-images/udnie.jpg
  • fast_neural_style/neural_style/__init__.py
  • fast_neural_style/neural_style/neural_style.py
  • fast_neural_style/neural_style/transformer_net.py
  • fast_neural_style/neural_style/utils.py
  • fast_neural_style/neural_style/vgg.py
  • fast_neural_style/README.md
  • imagenet/main.py
  • imagenet/README.md
  • imagenet/requirements.txt
  • LICENSE
  • mnist/main.py
  • mnist/README.md
  • mnist/requirements.txt
  • mnist_hogwild/main.py
  • mnist_hogwild/requirements.txt
  • mnist_hogwild/train.py
  • README.md
  • regression/main.py
  • regression/README.md
  • reinforcement_learning/actor_critic.py
  • reinforcement_learning/README.md
  • reinforcement_learning/reinforce.py
  • reinforcement_learning/requirements.txt
  • snli/model.py
  • snli/requirements.txt
  • snli/train.py
  • snli/util.py
  • super_resolution/data.py
  • super_resolution/dataset.py
  • super_resolution/main.py
  • super_resolution/model.py
  • super_resolution/README.md
  • super_resolution/super_resolve.py
  • time_sequence_prediction/generate_sine_wave.py
  • time_sequence_prediction/README.md
  • time_sequence_prediction/train.py
  • vae/main.py
  • vae/README.md
  • vae/requirements.txt
  • vae/results/.gitignore
  • word_language_model/data.py
  • word_language_model/data/wikitext-2/README
  • word_language_model/data/wikitext-2/test.txt
  • word_language_model/data/wikitext-2/train.txt
  • word_language_model/data/wikitext-2/valid.txt
  • word_language_model/generate.py
  • word_language_model/main.py
  • word_language_model/model.py
  • word_language_model/README.md
  • word_language_model/requirements.txt

Public Handling Notes

  • EXTRACTED: This page records public metadata and a source-grounded summary.
  • INFERRED: Full local preservation, when available, is for private/local use unless a license or explicit source policy makes public redistribution safe.
  • Do not treat this page as permission to republish unlicensed source text or code wholesale.