karpathy / lecun1989-repro

Related projects: ⓘ

• tysam-code / hlb-CIFAR10
  Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
  ☆1,213Updated 10 months ago
• karpathy / arxiv-sanity-lite
  arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors …
  ☆1,156Updated last year
• karpathy / randomfun
  Notebooks and various random fun
  ☆1,075Updated last year
• xl0 / lovely-tensors
  Tensors, for human consumption
  ☆1,096Updated 2 weeks ago
• clu0 / unet.cu
  UNet diffusion model in pure CUDA
  ☆562Updated 2 months ago
• EurekaLabsAI / tensor
  The Tensor (or Array)
  ☆388Updated last month
• srush / Triton-Puzzles
  Puzzles for learning Triton
  ☆966Updated this week
• EurekaLabsAI / mlp
  The Multilayer Perceptron Language Model
  ☆503Updated last month
• srush / LLM-Training-Puzzles
  What would you do with 1000 H100s...
  ☆816Updated 8 months ago
• karpathy / transformers
  🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
  ☆100Updated 2 years ago
• commaai / commavq
  commaVQ is a dataset of compressed driving video
  ☆289Updated 2 months ago
• srush / Transformer-Puzzles
  Puzzles for exploring transformers
  ☆293Updated last year
• EurekaLabsAI / micrograd
  The Autograd Engine
  ☆482Updated last week
• karpathy / makemore
  An autoregressive character-level language model for making more things
  ☆2,471Updated 3 months ago
• EurekaLabsAI / ngram
  The n-gram Language Model
  ☆1,288Updated last month
• tinygrad / teenygrad
  If tinygrad wasn't small enough for you...
  ☆631Updated 6 months ago
• JonasGeiping / cramming
  Cramming the training of a (BERT-type) language model into limited compute.
  ☆1,284Updated 3 months ago
• google-research / big_vision
  Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
  ☆2,206Updated 3 weeks ago
• google / learned_optimization
  ☆742Updated 5 months ago
• karpathy / cryptos
  Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes
  ☆1,565Updated 3 years ago
• mpezeshki / pytorch_forward_forward
  Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation
  ☆1,431Updated last year
• tanelp / tiny-diffusion
  A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.
  ☆633Updated 4 months ago
• BlackHC / toma
  Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory
  ☆419Updated 3 weeks ago
• jacobhilton / deep_learning_curriculum
  Language model alignment-focused deep learning curriculum
  ☆1,215Updated last month
• srush / annotated-mamba
  Annotated version of the Mamba paper
  ☆445Updated 6 months ago
• srush / Autodiff-Puzzles
  ☆325Updated 11 months ago
• johnmarktaylor91 / torchlens
  Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.
  ☆456Updated 2 weeks ago
• facebookresearch / schedule_free
  Schedule-Free Optimization in PyTorch
  ☆1,800Updated last month
• google-deepmind / penzai
  A JAX research toolkit for building, editing, and visualizing neural networks.
  ☆1,638Updated last week
• dair-ai / Transformers-Recipe
  🧠 A study guide to learn about Transformers
  ☆1,523Updated last year