Alternatives and similar repositories for dilated-self-attention:

Users that are interested in dilated-self-attention are comparing it to the libraries listed below

• fkodom / dilated-attention-pytorch
  (Unofficial) Implementation of dilated attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens" (https://arxiv.org/abs/2307…
  ☆50Updated last year
• imoneoi / multipack_sampler
  Multipack distributed sampler for fast padding-free training of LLMs
  ☆184Updated 5 months ago
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆177Updated 2 weeks ago
• bminixhofer / zett
  Code for Zero-Shot Tokenizer Transfer
  ☆121Updated 2 weeks ago
• RobertCsordas / moe_attention
  Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"
  ☆96Updated 4 months ago
• microsoft / mutransformers
  some common Huggingface transformers in maximal update parametrization (µP)
  ☆79Updated 2 years ago
• srush / do-we-need-attention
  ☆164Updated last year
• catie-aq / flashT5
  A fast implementation of T5/UL2 in PyTorch using Flash Attention
  ☆78Updated this week
• Knowledgator / TurboT5
  Truly flash T5 realization!
  ☆61Updated 8 months ago
• HazyResearch / based
  Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
  ☆219Updated last month
• hadasah / btm
  ☆72Updated 9 months ago
• llm-random / llm-random
  ☆180Updated this week
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆91Updated 2 months ago
• wdlctc / mini-s
  ☆43Updated 3 months ago
• HeegyuKim / torch-xla-SPMD
  Pytorch/XLA SPMD Test code in Google TPU
  ☆23Updated 9 months ago
• koayon / awesome-adaptive-computation
  A curated reading list of research in Adaptive Computation, Inference-Time Computation & Mixture of Experts (MoE).
  ☆137Updated 3 weeks ago
• jxmorris12 / bm25_pt
  minimal pytorch implementation of bm25 (with sparse tensors)
  ☆97Updated 10 months ago
• proger / hippogriff
  Griffin MQA + Hawk Linear RNN Hybrid
  ☆85Updated 9 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆113Updated last month
• IBM / ModuleFormer
  ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…
  ☆215Updated 9 months ago
• HanGuo97 / lq-lora
  ☆125Updated last year
• luyug / magix
  Supercharge huggingface transformers with model parallelism.
  ☆76Updated 3 months ago
• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆194Updated 2 months ago
• AblateIt / finetune-study
  Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.
  ☆82Updated last year
• whyNLP / LCKV
  Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…
  ☆147Updated last week
• EleutherAI / improved-t5
  Experiments for efforts to train a new and improved t5
  ☆77Updated 9 months ago
• for-ai / parameter-efficient-moe
  ☆250Updated last year
• booydar / LM-RMT
  Recurrent Memory Transformer
  ☆148Updated last year
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆102Updated last month