Alternatives and similar repositories for scion

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

• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆86Updated last year
• berlino / seq_icl
  ☆53Updated last year
• shikaiqiu / compute-better-spent
  ☆62Updated last year
• Leiay / looped_transformer
  ☆33Updated 2 years ago
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆69Updated last year
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆112Updated last month
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆174Updated 5 months ago
• maximzubkov / fft-scan
  Efficient PScan implementation in PyTorch
  ☆17Updated last year
• JeanKaddour / NoTrainNoGain
  Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)
  ☆81Updated 2 years ago
• NVIDIA-NeMo / Emerging-Optimizers
  ☆69Updated last week
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆62Updated last year
• insuhan / hyper-attn
  ☆83Updated 2 years ago
• sustcsonglin / mamba-triton
  ☆50Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆47Updated last year
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated 2 years ago
• samsja / muon_fsdp_2
  Muon fsdp 2
  ☆46Updated 4 months ago
• thinking-machines-lab / manifolds
  Supporting code for the blog post on modular manifolds.
  ☆104Updated 2 months ago
• RobertCsordas / moeut
  ☆89Updated last year
• JonasGeiping / linear_cross_entropy_loss
  A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.
  ☆73Updated last year
• cloneofsimo / min-fsdp
  ☆91Updated last year
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆38Updated last month
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated last year
• test-time-training / ttt-tk
  ☆41Updated last month
• zqOuO / GWT
  ☆13Updated 10 months ago
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆68Updated 2 months ago
• TianjinYellow / SPAM-Optimizer
  ☆36Updated 9 months ago
• dayal-kalra / low-memory-adam
  ☆13Updated 9 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
  ☆132Updated last month
• google-deepmind / spectral_ssm
  ☆34Updated last year
• zhixuan-lin / forgetting-transformer
  [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning
  ☆134Updated last month