Alternatives and similar repositories for abnormal-floats

Users that are interested in abnormal-floats are comparing it to the libraries listed below

• 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
• sustcsonglin / gated_linear_attention_layer
  ☆32Updated last year
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆85Updated last year
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated 2 years ago
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆47Updated last year
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆80Updated last year
• BlinkDL / SmallInitEmb
  LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence
  ☆61Updated 3 years ago
• berlino / seq_icl
  ☆53Updated last year
• samblouir / birdie
  ☆13Updated 6 months ago
• insuhan / hyper-attn
  ☆83Updated 2 years ago
• HomebrewML / Olmax
  HomebrewNLP in JAX flavour for maintable TPU-Training
  ☆51Updated last year
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆62Updated last year
• sustcsonglin / mamba-triton
  ☆50Updated last year
• cloneofsimo / min-fsdp
  ☆91Updated last year
• cat-state / tinypar
  ☆20Updated 2 years ago
• JeanKaddour / NoTrainNoGain
  Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)
  ☆81Updated 2 years ago
• renll / SeqBoat
  [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling
  ☆40Updated 2 years ago
• RobertCsordas / moe
  Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
  ☆38Updated 6 months ago
• HazyResearch / prefix-linear-attention
  ☆57Updated last year
• warner-benjamin / optimi
  Fast, Modern, and Low Precision PyTorch Optimizers
  ☆116Updated 3 months ago
• softmax1 / Flash-Attention-Softmax-N
  CUDA and Triton implementations of Flash Attention with SoftmaxN.
  ☆73Updated last year
• Ryu1845 / hyena-jax
  Implementation of Hyena Hierarchy in JAX
  ☆10Updated 2 years ago
• graphcore-research / out-of-the-box-fp8-training
  Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
  ☆46Updated last year
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆45Updated 2 years ago
• kyo-takano / chinchilla
  A toolkit for scaling law research ⚖
  ☆53Updated 10 months ago
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• srush / LLM-Talk
  ☆52Updated last year
• epfml / DenseFormer
  ☆82Updated last year
• shikaiqiu / compute-better-spent
  ☆62Updated last year