Alternatives and similar repositories for COSMOS

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

• RobertCsordas / moeut
  ☆89Updated last year
• berlino / seq_icl
  ☆53Updated last year
• wdlctc / mini-s
  ☆53Updated last year
• schwartz-lab-NLP / TOVA
  Token Omission Via Attention
  ☆128Updated last year
• JacobPfau / fillerTokens
  ☆75Updated last year
• VITA-Group / WeLore
  [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications
  ☆52Updated last month
• ScalingIntelligence / large_language_monkeys
  ☆110Updated last year
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆130Updated last year
• nanowell / Q-Sparse-LLM
  My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
  ☆33Updated last year
• TRI-ML / linear_open_lm
  A repository for research on medium sized language models.
  ☆77Updated last year
• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆79Updated last year
• jxiw / MambaByte
  [CoLM 24] Official Repository of MambaByte: Token-free Selective State Space Model
  ☆24Updated last year
• OpenEvaByte / evabyte
  EvaByte: Efficient Byte-level Language Models at Scale
  ☆111Updated 7 months ago
• whyNLP / LCKV
  Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…
  ☆157Updated 8 months ago
• kazuki-irie / kv-memory-brain
  Official Code Repository for the paper "Key-value memory in the brain"
  ☆31Updated 9 months ago
• zaydzuhri / softpick-attention
  Landing repository for the paper "Softpick: No Attention Sink, No Massive Activations with Rectified Softmax"
  ☆85Updated 3 months ago
• PiotrNawrot / sparse-frontier
  The evaluation framework for training-free sparse attention in LLMs
  ☆106Updated 2 months ago
• apple / ml-dataset-decomposition
  Official repo of dataset-decomposition paper [NeurIPS 2024]
  ☆20Updated 11 months ago
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆38Updated last month
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆45Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆86Updated last year
• NathanGodey / qfilters
  Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)
  ☆35Updated 9 months ago
• dmis-lab / Monet
  [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers
  ☆74Updated 5 months ago
• BorealisAI / flora-opt
  This is the official repository for the paper "Flora: Low-Rank Adapters Are Secretly Gradient Compressors" in ICML 2024.
  ☆105Updated last year
• sail-sg / SkyLadder
  The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
  ☆40Updated 2 months ago
• shawntan / stickbreaking-attention
  Stick-breaking attention
  ☆62Updated 5 months ago
• recursal / RADLADS-paper
  RADLADS training code
  ☆35Updated 7 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆180Updated 5 months ago
• Lagooon / LeanSTaR
  ☆42Updated last year
• StigLidu / TURN
  [ICML2025] Official Repo for Paper "Optimizing Temperature for Language Models with Multi-Sample Inference"
  ☆21Updated 10 months ago