Alternatives and similar repositories for stable-pretraining

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

• riverstone496 / awesome-second-order-optimization
  ☆27Updated last year
• autonomousvision / akorn
  [ICLR'25] Artificial Kuramoto Oscillatory Neurons
  ☆99Updated 3 weeks ago
• kvfrans / splus
  ☆115Updated 2 months ago
• BlackHC / neural_net_checklist
  ☆150Updated last year
• locuslab / torchdeq
  Modern Fixed Point Systems using Pytorch
  ☆103Updated last year
• facebookresearch / capi
  Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
  ☆116Updated 4 months ago
• kvfrans / jax-diffusion-transformer
  Implementation of Diffusion Transformer (DiT) in JAX
  ☆292Updated last year
• loeweX / RotatingFeatures
  Code for the paper: Rotating Features for Object Discovery
  ☆53Updated last year
• google-deepmind / nanodo
  ☆275Updated last year
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆93Updated 5 months ago
• AhmedImtiazPrio / grok-adversarial
  Deep Networks Grok All the Time and Here is Why
  ☆37Updated last year
• klieret / wandb-offline-sync-hook
  A convenient way to trigger synchronizations to wandb / Weights & Biases if your compute nodes don't have internet!
  ☆83Updated 3 weeks ago
• tovacinni / research-website-template
  React + Next.js template for research websites (for PhD students, researchers, etc)
  ☆187Updated 7 months ago
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆288Updated last month
• AllanYangZhou / universal_neural_functional
  ☆52Updated last year
• J-Rosser-UK / Torch2Jax-DeepSeek-R1-Distill-Qwen-1.5B
  Flax (Jax) implementation of DeepSeek-R1-Distill-Qwen-1.5B with weights ported from Hugging Face.
  ☆22Updated 6 months ago
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆301Updated last month
• AllanYangZhou / nfn
  NF-Layers for constructing neural functionals.
  ☆88Updated last year
• apoorvkh / academic-pretraining
  $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
  ☆143Updated 3 months ago
• yilundu / ired_code_release
  ☆69Updated last year
• lindermanlab / elk
  Scalable and Stable Parallelization of Nonlinear RNNS
  ☆20Updated last week
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆57Updated last week
• cloneofsimo / scaling-guide
  WIP
  ☆94Updated last year
• francoisfleuret / picogpt
  Minimal GPT (~350 lines with a simple task to test it)
  ☆62Updated 8 months ago
• hyperevolnet / Terminator
  The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.
  ☆39Updated 4 months ago
• kvfrans / jax-flow
  Flow-matching algorithms in JAX
  ☆104Updated last year
• modula-systems / modula
  🧱 Modula software package
  ☆231Updated 2 weeks ago
• idiap / sigma-gpt
  σ-GPT: A New Approach to Autoregressive Models
  ☆67Updated last year
• young-geng / scalax
  A simple library for scaling up JAX programs
  ☆143Updated 10 months ago
• Sohl-Dickstein / fractal
  The boundary of neural network trainability is fractal
  ☆215Updated last year