Alternatives and similar repositories for RetNet

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

• OpenNLPLab / HGRN
  [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…
  ☆66Updated last year
• prateekstark / retnet
  ☆14Updated 2 years ago
• HazyResearch / prefix-linear-attention
  ☆58Updated last year
• lucidrains / gateloop-transformer
  Implementation of GateLoop Transformer in Pytorch and Jax
  ☆92Updated last year
• proger / hippogriff
  Griffin MQA + Hawk Linear RNN Hybrid
  ☆88Updated last year
• dtunai / Griffin-Jax
  Jax implementation of "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"
  ☆15Updated last year
• deep-spin / infinite-former
  ☆67Updated last year
• PiotrNawrot / dynamic-pooling
  Efficient Transformers with Dynamic Token Pooling
  ☆67Updated 2 years ago
• juvi21 / CoPE-cuda
  Contextual Position Encoding but with some custom CUDA Kernels https://arxiv.org/abs/2405.18719
  ☆22Updated last year
• kyegomez / Griffin
  Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"
  ☆56Updated 3 months ago
• dashstander / block-recurrent-transformer
  Pytorch implementation of "Block Recurrent Transformers" (Hutchins & Schlag et al., 2022)
  ☆85Updated 3 years ago
• sustcsonglin / mamba-triton
  ☆51Updated 2 years ago
• sustcsonglin / gated_linear_attention_layer
  ☆32Updated 2 years ago
• McGill-NLP / length-generalization
  Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023
  ☆137Updated last year
• google-deepmind / randomized_positional_encodings
  Randomized Positional Encodings Boost Length Generalization of Transformers
  ☆82Updated last year
• OpenMOSE / RWKV-Infer
  A large-scale RWKV v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy…
  ☆47Updated 3 months ago
• SmerkyG / RWKV_Explained
  RWKV, in easy to read code
  ☆72Updated 10 months ago
• kjslag / spacebyte
  A byte-level decoder architecture that matches the performance of tokenized Transformers.
  ☆67Updated last year
• nanowell / Q-Sparse-LLM
  My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
  ☆33Updated last year
• kyegomez / Infini-attention
  Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…
  ☆58Updated last week
• openfeedback / superhf
  Open-source Human Feedback Library
  ☆11Updated 2 years ago
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆56Updated last year
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated 2 years ago
• johanwind / wind_rwkv
  ☆27Updated 6 months ago
• RobertCsordas / moe
  Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
  ☆38Updated 7 months ago
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆92Updated 2 years ago
• lucidrains / PEER-pytorch
  Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind
  ☆134Updated 3 months ago
• basusourya / mirostat
  Code for the paper-"Mirostat: A Perplexity-Controlled Neural Text Decoding Algorithm" (https://arxiv.org/abs/2007.14966).
  ☆61Updated 3 years ago
• piotrpiekos / MoSA
  User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…
  ☆28Updated 9 months ago
• adihaviv / nopos
  ☆22Updated 2 years ago