Alternatives and similar repositories for state-space-models:

Users that are interested in state-space-models are comparing it to the libraries listed below

• KhoomeiK / complexity-scaling
  gzip Predicts Data-dependent Scaling Laws
  ☆34Updated 9 months ago
• evanatyourservice / llm-jax
  Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.
  ☆17Updated this week
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆83Updated last month
• joey00072 / microjax
  Jax like function transformation engine but micro, microjax
  ☆30Updated 4 months ago
• xjdr-alt / muzero_sketch
  ☆38Updated 7 months ago
• vtabbott / Algebraic-NCD
  A package for defining deep learning models using categorical algebraic expressions.
  ☆60Updated 7 months ago
• leloykun / modded-nanogpt
  NanoGPT (124M) quality in 2.67B tokens
  ☆28Updated 3 weeks ago
• NousResearch / StripedHyenaTrainer
  ☆60Updated last year
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• catid / lllm
  Latent Large Language Models
  ☆17Updated 6 months ago
• Jaykef / Triton-nanoGPT
  Custom triton kernels for training Karpathy's nanoGPT.
  ☆18Updated 5 months ago
• euclaise / supertrainer2000
  ☆49Updated last year
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated 5 months ago
• LucasPrietoAl / grokking-at-the-edge-of-numerical-stability
  ☆89Updated 2 months ago
• epfml / DenseFormer
  ☆79Updated 11 months ago
• google-deepmind / asyncdiloco
  ☆43Updated last year
• ClashLuke / SOAP
  ☆21Updated 4 months ago
• tobiaskatsch / GatedLinearRNN
  ☆27Updated last year
• lucaslingle / mu_transformer
  Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.
  ☆30Updated 3 months ago
• CarperAI / treasure_trove
  ☆22Updated last year
• jadechip / nanoXLSTM
  The simplest, fastest repository for training/finetuning medium-sized xLSTMs.
  ☆42Updated 9 months ago
• ethansmith2000 / TransformerExperiments
  ☆19Updated 5 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆100Updated 4 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆122Updated 11 months ago
• google-deepmind / mishax
  ☆124Updated this week