Alternatives and similar repositories for naturalattention

Users that are interested in naturalattention are comparing it to the libraries listed below

• neoneye / ARC-Interactive-History-Dataset
  The history files when recording human interaction while solving ARC tasks
  ☆112Updated 2 weeks ago
• neurallambda / neurallambda
  Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.
  ☆261Updated 7 months ago
• vtabbott / Algebraic-NCD
  A package for defining deep learning models using categorical algebraic expressions.
  ☆61Updated 11 months ago
• nreHieW / r-nn
  Tensor library with autograd using only Rust's standard library
  ☆68Updated 11 months ago
• timaeus-research / devinterp
  Tools for studying developmental interpretability in neural networks.
  ☆95Updated this week
• adamnemecek / traceoid.ai
  ☆97Updated 6 months ago
• xu3kev / BARC
  Bootstrapping ARC
  ☆130Updated 7 months ago
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆87Updated 3 months ago
• xjdr-alt / simple_transformer
  Simple Transformer in Jax
  ☆137Updated last year
• jerber / lang-jepa
  ☆114Updated 6 months ago
• gpoesia / peano
  An environment for learning formal mathematical reasoning from scratch
  ☆70Updated 10 months ago
• victorvikram / ConceptARC
  Materials for ConceptARC paper
  ☆95Updated 7 months ago
• iliao2345 / CompressARC
  ☆157Updated 2 months ago
• neoneye / arc-notes
  My writings about ARC (Abstraction and Reasoning Corpus)
  ☆77Updated this week
• da-fr / arc-prize-2024
  Our solution for the arc challenge 2024
  ☆149Updated last week
• michaelhodel / arc-dsl
  Domain Specific Language for the Abstraction and Reasoning Corpus
  ☆267Updated 8 months ago
• neoneye / arc-dataset-collection
  Multiple datasets for ARC (Abstraction and Reasoning Corpus)
  ☆70Updated 3 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆139Updated this week
• haraschax / nograd
  Gradient descent is cool and all, but what if we could delete it?
  ☆103Updated last week
• wbrickner / noise_step
  noise_step: Training in 1.58b With No Gradient Memory
  ☆219Updated 6 months ago
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated 8 months ago
• rgreenblatt / arc_draw_more_samples_pub
  Draw more samples
  ☆191Updated last year
• alan-cooney / transformer-from-scratch
  Decoder only transformer, built from scratch with PyTorch
  ☆30Updated last year
• okarthikb / state-space-models
  ☆27Updated 11 months ago
• LucasPrietoAl / grokking-at-the-edge-of-numerical-stability
  ☆98Updated 5 months ago
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆190Updated last year
• reissbaker / clevergpt
  Training GPTs to solve interaction nets
  ☆17Updated 10 months ago
• MatX-inc / seqax
  seqax = sequence modeling + JAX
  ☆162Updated 2 weeks ago
• modula-systems / modula
  🧱 Modula software package
  ☆200Updated 3 months ago
• doomslide / attention-graph
  A graph visualization of attention
  ☆56Updated last month