Alternatives and similar repositories for stable-pretraining

Users that are interested in stable-pretraining are comparing it to the libraries listed below

• BlackHC / neural_net_checklist
  ☆215Updated last year
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆337Updated 6 months ago
• autonomousvision / akorn
  [ICLR'25] Artificial Kuramoto Oscillatory Neurons
  ☆107Updated 3 months ago
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆347Updated 2 months ago
• nikhilvyas / SOAP
  ☆238Updated last year
• google-deepmind / nanodo
  ☆289Updated last year
• modula-systems / modula
  🧱 Modula software package
  ☆322Updated 5 months ago
• kvfrans / splus
  ☆123Updated 7 months ago
• NX-AI / xlstm-jax
  Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…
  ☆105Updated last year
• BARL-SSL / reptrix
  Library that provides metrics to assess representation quality
  ☆20Updated 11 months ago
• Atcold / Energy-Book
  Deep Learning, an Energy Approach
  ☆239Updated 7 months ago
• lixilinx / psgd_torch
  Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…
  ☆191Updated 2 weeks ago
• HomebrewML / HeavyBall
  Efficient optimizers
  ☆280Updated last month
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆107Updated 2 months ago
• locuslab / torchdeq
  Modern Fixed Point Systems using Pytorch
  ☆125Updated 2 years ago
• kvfrans / jax-diffusion-transformer
  Implementation of Diffusion Transformer (DiT) in JAX
  ☆305Updated last year
• facebookresearch / capi
  Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
  ☆129Updated 2 weeks ago
• PeaBrane / mamba-tiny
  Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).
  ☆130Updated last year
• eemlcommunity / PracticalSessions2023
  ☆69Updated 2 years ago
• mila-iqia / ResearchTemplate
  Research Project Template Repository
  ☆40Updated 2 weeks ago
• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆117Updated last month
• riverstone496 / awesome-second-order-optimization
  ☆27Updated 4 months ago
• CLAIRE-Labo / python-ml-research-template
  A template for starting reproducible Python machine-learning projects with hardware acceleration. Find an example at https://github.com/C…
  ☆114Updated 7 months ago
• fferflo / einx
  Universal Notation for Tensor Operations in Python.
  ☆463Updated 9 months ago
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆196Updated 3 weeks ago
• bremen79 / parameterfree
  Parameter-Free Optimizers for Pytorch
  ☆130Updated last year
• shikaiqiu / compute-better-spent
  ☆62Updated last year
• lindermanlab / elk
  Scalable and Stable Parallelization of Nonlinear RNNS
  ☆28Updated 3 months ago
• Sohl-Dickstein / fractal
  The boundary of neural network trainability is fractal
  ☆221Updated last year
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year