Alternatives and similar repositories for grokking-at-the-edge-of-numerical-stability:

Users that are interested in grokking-at-the-edge-of-numerical-stability are comparing it to the libraries listed below

• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆116Updated 2 months ago
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• epfml / DenseFormer
  ☆78Updated 10 months ago
• schwartz-lab-NLP / TOVA
  Token Omission Via Attention
  ☆123Updated 4 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆76Updated 2 months ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆103Updated 2 months ago
• RobertCsordas / moeut
  ☆71Updated 6 months ago
• lucidrains / grokfast-pytorch
  Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
  ☆95Updated last month
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆95Updated 3 months ago
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆181Updated last month
• Zyphra / Zamba2
  PyTorch implementation of models from the Zamba2 series.
  ☆176Updated 3 weeks ago
• huyphan168 / PEER
  Mixture of A Million Experts
  ☆40Updated 6 months ago
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆81Updated last week
• kjslag / spacebyte
  A byte-level decoder architecture that matches the performance of tokenized Transformers.
  ☆65Updated 9 months ago
• Mihaiii / backtrack_sampler
  An easy-to-understand framework for LLM samplers that rewind and revise generated tokens
  ☆130Updated this week
• cloneofsimo / min-fsdp
  ☆75Updated 7 months ago
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆152Updated 3 months ago
• facebookresearch / MemoryMosaics
  Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.
  ☆39Updated 3 weeks ago
• euclaise / supertrainer2000
  ☆49Updated 11 months ago
• lucidrains / PEER-pytorch
  Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind
  ☆118Updated 5 months ago
• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆181Updated 2 months ago
• sebulo / LoQT
  ☆79Updated 3 months ago
• berlino / seq_icl
  ☆51Updated 9 months ago
• kyleliang919 / Online-Subspace-Descent
  This repo is based on https://github.com/jiaweizzhao/GaLore
  ☆24Updated 5 months ago
• SeunghyunSEO / optimized_hf_llama_class_for_training
  ☆47Updated 5 months ago
• wdlctc / mini-s
  ☆44Updated 3 months ago
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆43Updated 7 months ago
• jadechip / nanoXLSTM
  The simplest, fastest repository for training/finetuning medium-sized xLSTMs.
  ☆39Updated 8 months ago