Alternatives and similar repositories for RFA

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

• sarthmit / Compositional-Attention
  Code to reproduce the results for Compositional Attention
  ☆59Updated 3 years ago
• xuanqing94 / FLOATER
  Learning to Encode Position for Transformer with Continuous Dynamical Model
  ☆59Updated 5 years ago
• microsoft / Stochastic-Mixture-of-Experts
  This package implements THOR: Transformer with Stochastic Experts.
  ☆65Updated 4 years ago
• bergen / EdgeTransformer
  ☆22Updated 4 years ago
• sanagno / adaptively_sparse_attention
  ☆22Updated 2 years ago
• HKUNLP / efficient-attention
  [EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling
  ☆87Updated 2 years ago
• Shark-NLP / CAB
  ☆31Updated 2 years ago
• radarFudan / Curse-of-memory
  Curse-of-memory phenomenon of RNNs in sequence modelling
  ☆19Updated 7 months ago
• dguo98 / DiffPruning
  Parameter Efficient Transfer Learning with Diff Pruning
  ☆74Updated 4 years ago
• lsj2408 / URPE
  [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)
  ☆34Updated 2 years ago
• varunnair18 / FISH
  Code for "Training Neural Networks with Fixed Sparse Masks" (NeurIPS 2021).
  ☆59Updated 3 years ago
• microsoft / EfficientLongSequenceModeling
  ☆52Updated 2 years ago
• srush / mamba-scans
  Blog post
  ☆17Updated last year
• VITA-Group / Random-MoE-as-Dropout
  [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…
  ☆56Updated 2 years ago
• RobertCsordas / ndr
  The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".
  ☆34Updated 6 months ago
• CyndxAI / QKNorm
  Code for the paper "Query-Key Normalization for Transformers"
  ☆50Updated 4 years ago
• OpenNLPLab / HGRN
  [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…
  ☆66Updated last year
• ghazi-f / QKVAE
  Implementation of QKVAE
  ☆11Updated 2 years ago
• ischlag / fast-weight-transformers
  Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.
  ☆111Updated 4 years ago
• polo5 / FDS
  Gradient-based Hyperparameter Optimization Over Long Horizons
  ☆14Updated 4 years ago
• pkuzengqi / Skyformer
  Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)
  ☆63Updated 3 years ago
• lancopku / Explicit-Sparse-Transformer
  code for Explicit Sparse Transformer
  ☆61Updated 2 years ago
• asappresearch / flop
  Pytorch library for factorized L0-based pruning.
  ☆45Updated 2 years ago
• yuPeiyu98 / Latent-Diffusion-EBM
  [ICML 2022] Latent Diffusion Energy-Based Model for Interpretable Text Modeling
  ☆67Updated 3 years ago
• RakitinDen / pytorch-recursive-gumbel-max-trick
  Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces, NeurIPS 2021
  ☆13Updated 4 years ago
• OpenNLPLab / Tnn
  [ICLR 2023] Official implementation of Transnormer in our ICLR 2023 paper - Toeplitz Neural Network for Sequence Modeling
  ☆81Updated last year
• berlino / gated_linear_attention
  ☆106Updated last year
• IDSIA / recurrent-fwp
  Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)
  ☆51Updated 6 months ago
• RobertCsordas / linear_layer_as_attention
  The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …
  ☆16Updated 6 months ago
• jungokasai / T2R
  ☆14Updated 3 years ago