misko / human_descent

Related projects ⓘ

Alternatives and complementary repositories for human_descent

• itsdaniele / jeometric
  Graph neural networks in JAX.
  ☆67Updated 4 months ago
• SamsungSAILMontreal / AnyMolGenCritic
  ☆20Updated last month
• xjdr-alt / simple_transformer
  Simple Transformer in Jax
  ☆115Updated 4 months ago
• vtabbott / Algebraic-NCD
  A package for defining deep learning models using categorical algebraic expressions.
  ☆56Updated 3 months ago
• jxbz / modula
  Scalable neural net training via automatic normalization in the modular norm.
  ☆119Updated 2 months ago
• ml-jku / GINNs-Geometry-informed-Neural-Networks
  ☆89Updated this week
• kvfrans / jax-flow
  Flow-matching algorithms in JAX
  ☆74Updated 3 months ago
• Sohl-Dickstein / fractal
  The boundary of neural network trainability is fractal
  ☆161Updated 9 months ago
• Artur-Galstyan / statedict2pytree
  ☆40Updated 4 months ago
• smsharma / minified-generative-models
  Bare-bones implementations of some generative models in Jax: diffusion, normalizing flows, consistency models, flow matching, (beta)-VAEs…
  ☆123Updated 10 months ago
• cgarciae / einop
  ☆58Updated 2 years ago
• helblazer811 / diffusion-visualizations
  Visualizations of the theory behind diffusion models.
  ☆74Updated 6 months ago
• irregular-rhomboid / EAI-Math-Reading-Group
  Resources from the EleutherAI Math Reading Group
  ☆50Updated last month
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆95Updated 6 months ago
• kvfrans / jax-diffusion-transformer
  Implementation of Diffusion Transformer (DiT) in JAX
  ☆252Updated 5 months ago
• cloneofsimo / scaling-guide
  WIP
  ☆89Updated 2 months ago
• KellerJordan / Muon
  Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead
  ☆69Updated this week
• bhosmer / mm
  ☆113Updated last week
• lucidrains / grokfast-pytorch
  Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
  ☆84Updated 2 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆84Updated last week
• KindXiaoming / BIMT
  Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
  ☆162Updated last year
• AakashKumarNain / mistral_jax
  This is a port of Mistral-7B model in JAX
  ☆30Updated 4 months ago
• dvruette / barrel-rec-pytorch
  ☆53Updated 9 months ago
• LiibanMo / scikit-jax
  Your favourite classical machine learning algos on the GPU/TPU
  ☆20Updated last month
• mcleish7 / arithmetic
  Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)
  ☆177Updated 5 months ago
• KellerJordan / cifar10-airbench
  94% on CIFAR-10 in 2.59 seconds 💨 96% in 27 seconds
  ☆168Updated this week
• thomasahle / tensorgrad
  Tensor Network Library with Autograd
  ☆148Updated last week
• nikhilvyas / SOAP
  ☆122Updated this week
• apoorvkh / academic-pretraining
  $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
  ☆93Updated last week
• MatX-inc / seqax
  seqax = sequence modeling + JAX
  ☆132Updated 3 months ago