Alternatives and similar repositories for MoSA:

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

• sustcsonglin / gated_linear_attention_layer
  ☆32Updated last year
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆54Updated 8 months ago
• kyegomez / MultiQueryAttention
  This is a simple torch implementation of the high performance Multi-Query Attention
  ☆17Updated last year
• duykhuongnguyen / LASeR-MAB
  Code for paper: "LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits"
  ☆13Updated 7 months ago
• yale-nlp / refdpo
  ☆16Updated 9 months ago
• OpenNLPLab / HGRN
  [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…
  ☆64Updated last year
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆60Updated last year
• wang-kee / LiNeS
  Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"
  ☆26Updated 6 months ago
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆27Updated last year
• kyegomez / Reka-Torch
  Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorch
  ☆30Updated 2 weeks ago
• HazyResearch / prefix-linear-attention
  ☆53Updated 10 months ago
• Doraemonzzz / hgru2-pytorch
  ☆23Updated 7 months ago
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆45Updated 9 months ago
• thunlp / SparsingLaw
  The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".
  ☆21Updated 5 months ago
• pixeli99 / MixLN
  [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…
  ☆21Updated 4 months ago
• radarFudan / Curse-of-memory
  Curse-of-memory phenomenon of RNNs in sequence modelling
  ☆19Updated this week
• lucidrains / transformer-lm-gan
  Explorations into adversarial losses on top of autoregressive loss for language modeling
  ☆35Updated 2 months ago
• sjelassi / transformers_ssm_copy
  ☆31Updated last year
• 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 last year
• yikangshen / megablocks
  ☆20Updated 11 months ago
• kamanphoebe / Look-into-MoEs
  [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models
  ☆51Updated 3 months ago
• ducdauge / sft-llm
  Scaling Sparse Fine-Tuning to Large Language Models
  ☆15Updated last year
• SprocketLab / sparse_matrix_fine_tuning
  Official repository for ICML 2024 paper "MoRe Fine-Tuning with 10x Fewer Parameters"
  ☆18Updated this week
• akhilkedia / TranformersGetStable
  [ICML 2024] Official Repository for the paper "Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models"
  ☆10Updated 9 months ago
• princeton-nlp / ELIZA-Transformer
  [NAACL 2025] Representing Rule-based Chatbots with Transformers
  ☆20Updated 3 months ago
• sail-sg / SkyLadder
  The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
  ☆29Updated last month
• princeton-pli / MeCo
  Code for preprint "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"
  ☆37Updated this week
• 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…
  ☆51Updated 2 years ago
• lsj2408 / URPE
  [NeurIPS 2022] Your Transformer May Not be as Powerful as You Expect (official implementation)
  ☆34Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆43Updated 7 months ago