Alternatives and similar repositories for scaling

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

• google-deepmind / mishax
  ☆151Updated 4 months ago
• EleutherAI / improved-t5
  Experiments for efforts to train a new and improved t5
  ☆76Updated last year
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆185Updated 6 months ago
• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆109Updated 10 months ago
• epfml / DenseFormer
  ☆82Updated last year
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆85Updated last week
• OpenEvaByte / evabyte
  EvaByte: Efficient Byte-level Language Models at Scale
  ☆114Updated 8 months ago
• euclaise / supertrainer2000
  ☆50Updated last year
• evanatyourservice / llm-jax
  Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.
  ☆18Updated 5 months ago
• yixiaoer / tpux
  A set of Python scripts that makes your experience on TPU better
  ☆55Updated 4 months ago
• KhoomeiK / complexity-scaling
  gzip Predicts Data-dependent Scaling Laws
  ☆34Updated last year
• google-deepmind / asyncdiloco
  ☆47Updated 2 years ago
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆89Updated last year
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆131Updated last year
• microsoft / mutransformers
  some common Huggingface transformers in maximal update parametrization (µP)
  ☆87Updated 3 years ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• arcee-ai / DAM
  ☆55Updated last year
• kanishkg / stream-of-search
  Repository for the paper Stream of Search: Learning to Search in Language
  ☆152Updated 11 months ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆87Updated last year
• joshuacnf / Ctrl-G
  ☆105Updated last year
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆175Updated last year
• RobertCsordas / moeut
  ☆91Updated last year
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆136Updated last year
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆114Updated 2 months ago
• cat-state / tinypar
  ☆20Updated 2 years ago
• cloneofsimo / min-fsdp
  ☆92Updated last year
• JacobPfau / fillerTokens
  ☆75Updated last year
• jxmorris12 / cde
  code for training & evaluating Contextual Document Embedding models
  ☆202Updated 8 months ago
• NousResearch / StripedHyenaTrainer
  ☆62Updated 2 years ago
• vicksEmmanuel / latent-gemma
  ☆26Updated last year