Alternatives and similar repositories for PSI

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

• knsiczarnamagia / kaggle-tutorial
  Kick-off repository for starting with Kaggle!
  ☆12Updated 10 months ago
• cloneofsimo / minRF
  Minimal implementation of scalable rectified flow transformers, based on SD3's approach
  ☆611Updated last year
• er537 / MuP
  ☆10Updated last year
• HomebrewML / HeavyBall
  Efficient optimizers
  ☆269Updated last week
• lucidrains / nGPT-pytorch
  Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI
  ☆290Updated 4 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆83Updated 10 months ago
• knsiczarnamagia / wave
  ☆27Updated 9 months ago
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆313Updated 3 months ago
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆75Updated 9 months ago
• cloneofsimo / vqgan-training
  Train VAE like a boss
  ☆293Updated 11 months ago
• Algomancer / Bayesian-Flow-Networks
  A simple implimentation of Bayesian Flow Networks (BFN)
  ☆240Updated last year
• zyushun / Adam-mini
  Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793
  ☆439Updated 5 months ago
• apapiu / transformer_latent_diffusion
  Text to Image Latent Diffusion using a Transformer core
  ☆209Updated last year
• SwayStar123 / microdiffusion
  ☆49Updated 7 months ago
• Animadversio / DiffusionFromScratch
  Rebuild the Stable Diffusion Model in a single python script. Tutorial for Harvard ML from Scratch Series
  ☆216Updated 8 months ago
• clu0 / unet.cu
  UNet diffusion model in pure CUDA
  ☆649Updated last year
• cloneofsimo / minSDXL
  Huggingface-compatible SDXL Unet implementation that is readily hackable
  ☆426Updated 2 years ago
• HazyResearch / flash-fft-conv
  FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
  ☆329Updated 9 months ago
• dome272 / Wuerstchen
  Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models
  ☆552Updated last year
• cloneofsimo / minSAE
  ☆30Updated 10 months ago
• ironjr / grokfast
  Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
  ☆562Updated last year
• AI-Hypercomputer / maxdiffusion
  ☆268Updated this week
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• nanowell / AdEMAMix-Optimizer-Pytorch
  The AdEMAMix Optimizer: Better, Faster, Older.
  ☆186Updated last year
• srush / annotated-mamba
  Annotated version of the Mamba paper
  ☆489Updated last year
• thinking-machines-lab / manifolds
  Supporting code for the blog post on modular manifolds.
  ☆77Updated 3 weeks ago
• BobMcDear / attorch
  A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
  ☆577Updated 2 months ago
• danielvegamyhre / ml-perf-reading-group
  My annotated papers and meeting recordings for the EleutherAI ML Performance research paper reading group
  ☆21Updated 3 weeks ago
• tmabraham / diffusion_reading_group
  Diffusion Reading Group at EleutherAI
  ☆324Updated 2 years ago
• PeaBrane / mamba-tiny
  Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).
  ☆124Updated last year