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 11 months ago
• knsiczarnamagia / wave
  ☆27Updated 11 months ago
• HomebrewML / HeavyBall
  Efficient optimizers
  ☆276Updated 2 weeks ago
• cloneofsimo / minRF
  Minimal implementation of scalable rectified flow transformers, based on SD3's approach
  ☆620Updated last year
• cloneofsimo / vqgan-training
  Train VAE like a boss
  ☆301Updated last year
• apapiu / transformer_latent_diffusion
  Text to Image Latent Diffusion using a Transformer core
  ☆215Updated last year
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated 11 months ago
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆326Updated 2 weeks ago
• leloykun / adaptive-muon
  A single-line modification to any (dualizer-based) optimizer that allows the optimizer to adapt to the scale of the gradients as they cha…
  ☆17Updated 10 months ago
• danielvegamyhre / ml-perf-reading-group
  EleutherAI ML Performance reading group repository (slides, meeting recordings, annotated papers)
  ☆23Updated 3 weeks ago
• ironjr / grokfast
  Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
  ☆564Updated last year
• clu0 / unet.cu
  UNet diffusion model in pure CUDA
  ☆655Updated last year
• phys-ai / concept_graphs
  ☆14Updated last year
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• surkovv / sdxl-unbox
  Sparse Autoencoders for Stable Diffusion XL models.
  ☆76Updated last month
• nanowell / AdEMAMix-Optimizer-Pytorch
  The AdEMAMix Optimizer: Better, Faster, Older.
  ☆186Updated last year
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆323Updated 4 months ago
• EleutherAI / cookbook
  Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
  ☆826Updated 4 months ago
• cloneofsimo / minSDXL
  Huggingface-compatible SDXL Unet implementation that is readily hackable
  ☆432Updated 2 years ago
• zyushun / Adam-mini
  Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793
  ☆445Updated 6 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆663Updated last week
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆75Updated 11 months ago
• rasbt / dora-from-scratch
  LoRA and DoRA from Scratch Implementations
  ☆215Updated last year
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆173Updated 5 months ago
• kvfrans / jax-diffusion-transformer
  Implementation of Diffusion Transformer (DiT) in JAX
  ☆296Updated last year
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆194Updated last year
• nikhilvyas / SOAP
  ☆224Updated 11 months ago
• tysam-code / hlb-gpt
  Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…
  ☆352Updated last year
• BobMcDear / attorch
  A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
  ☆583Updated 3 months ago
• berndprach / 1LipschitzLayersCompared
  ☆12Updated last year