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
• JonasGeiping / linear_cross_entropy_loss
  A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.
  ☆70Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆84Updated 11 months ago
• shikaiqiu / compute-better-spent
  ☆58Updated last year
• Leiay / looped_transformer
  ☆32Updated last year
• JeanKaddour / NoTrainNoGain
  Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)
  ☆80Updated 2 years ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆164Updated 3 months ago
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated last year
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆68Updated last year
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆107Updated 4 months ago
• samsja / muon_fsdp_2
  Muon fsdp 2
  ☆44Updated 2 months ago
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆45Updated last year
• cloneofsimo / min-fsdp
  ☆91Updated last year
• RobertCsordas / moeut
  ☆85Updated last year
• zqOuO / GWT
  ☆13Updated 8 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆83Updated 10 months ago
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆61Updated last year
• dayal-kalra / low-memory-adam
  ☆13Updated 7 months ago
• google-deepmind / spectral_ssm
  ☆34Updated last year
• sustcsonglin / mamba-triton
  ☆48Updated last year
• test-time-training / ttt-tk
  ☆41Updated 6 months ago
• huyphan168 / PEER
  Mixture of A Million Experts
  ☆48Updated last year
• insuhan / hyper-attn
  ☆83Updated last year
• maximzubkov / fft-scan
  Efficient PScan implementation in PyTorch
  ☆16Updated last year
• apple / ml-ademamix
  ☆67Updated 10 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
  ☆129Updated last year
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆34Updated 11 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• edwardmilsom / function-space-learning-rates-paper
  Code for the paper "Function-Space Learning Rates"
  ☆23Updated 4 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 last year