Alternatives and similar repositories for scion

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

• berlino / seq_icl
  ☆53Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆89Updated last year
• zqOuO / GWT
  ☆13Updated last year
• shikaiqiu / compute-better-spent
  ☆62Updated last year
• JeanKaddour / NoTrainNoGain
  Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)
  ☆81Updated 2 years ago
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated 2 years ago
• Leiay / looped_transformer
  ☆34Updated 2 years ago
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆113Updated 3 months ago
• samsja / muon_fsdp_2
  Muon fsdp 2
  ☆53Updated 6 months ago
• test-time-training / ttt-tk
  ☆44Updated 3 months ago
• sustcsonglin / mamba-triton
  ☆51Updated 2 years ago
• maximzubkov / fft-scan
  Efficient PScan implementation in PyTorch
  ☆17Updated 2 years ago
• JonasGeiping / linear_cross_entropy_loss
  A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.
  ☆75Updated last year
• fangyuan-ksgk / selective-attention-transformer
  Unofficial Implementation of Selective Attention Transformer
  ☆20Updated last year
• dayal-kalra / low-memory-adam
  ☆14Updated 11 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆47Updated last year
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆187Updated 3 weeks ago
• TianjinYellow / SPAM-Optimizer
  ☆36Updated 11 months ago
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆62Updated last year
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆47Updated last year
• google-deepmind / spectral_ssm
  ☆35Updated last year
• srush / mamba-primer
  ☆39Updated last year
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆70Updated last year
• insuhan / hyper-attn
  ☆83Updated 2 years ago
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆40Updated 3 months ago
• shawntan / stickbreaking-attention
  Stick-breaking attention
  ☆62Updated 7 months ago
• lucidrains / pause-transformer
  Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…
  ☆53Updated 2 years ago
• sjelassi / transformers_ssm_copy
  ☆35Updated last year
• sustcsonglin / gated_linear_attention_layer
  ☆32Updated 2 years ago