Skip to content
Change the repository type filter

All

    Repositories list

    • minions

      Public
      Big & Small LLMs working together
      Python
      1351.2k111Updated Oct 21, 2025Oct 21, 2025
    • Tile primitives for speedy kernels
      Cuda
      1902.8k3817Updated Oct 18, 2025Oct 18, 2025
    • Storing long contexts in tiny caches with self-study
      Python
      1720111Updated Oct 17, 2025Oct 17, 2025
    • kernels, of the mega variety
      Python
      2658741Updated Sep 28, 2025Sep 28, 2025
    • bwler

      Public
      Official repo for BWLer: Barycentric Weight Layer
      Python
      32300Updated Sep 26, 2025Sep 26, 2025
    • zoology

      Public
      Understand and test language model architectures on synthetic tasks.
      Python
      3823311Updated Sep 25, 2025Sep 25, 2025
    • Python
      22200Updated Sep 4, 2025Sep 4, 2025
    • C++
      0300Updated Aug 26, 2025Aug 26, 2025
    • WONDERBREAD benchmark + dataset for BPM tasks
      Jupyter Notebook
      72800Updated Jul 30, 2025Jul 30, 2025
    • based

      Public
      Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
      Python
      1724130Updated Jun 6, 2025Jun 6, 2025
    • hyena-dna

      Public
      Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena
      Assembly
      103725337Updated Apr 22, 2025Apr 22, 2025
    • Python
      5700Updated Mar 18, 2025Mar 18, 2025
    • lolcats

      Public
      Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
      Python
      2524880Updated Jan 31, 2025Jan 31, 2025
    • aioli

      Public
      Aioli: A unified optimization framework for language model data mixing
      Jupyter Notebook
      42710Updated Jan 17, 2025Jan 17, 2025
    • FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
      C++
      29329184Updated Dec 28, 2024Dec 28, 2024
    • m2

      Public
      Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"
      Assembly
      42560252Updated Dec 28, 2024Dec 28, 2024
    • meerkat

      Public
      Explore and understand your training and validation data.
      Python
      4584783Updated Dec 24, 2024Dec 24, 2024
    • smoothie

      Public
      Jupyter Notebook
      31300Updated Dec 10, 2024Dec 10, 2024
    • train-tk

      Public
      train with kittens!
      Python
      7.9k6300Updated Oct 25, 2024Oct 25, 2024
    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      11k100Updated Oct 14, 2024Oct 14, 2024
    • Automating enterprise workflows with multimodal agents
      Jupyter Notebook
      1311200Updated Oct 9, 2024Oct 9, 2024
    • An open science effort to benchmark legal reasoning in foundation models
      Python
      7650357Updated Aug 25, 2024Aug 25, 2024
    • hgcn

      Public
      Hyperbolic Graph Convolutional Networks in PyTorch.
      Python
      115646203Updated Jul 25, 2024Jul 25, 2024
    • manifest

      Public
      Prompt programming with FMs.
      Python
      4544362Updated Jul 22, 2024Jul 22, 2024
    • Python
      25610Updated Jul 9, 2024Jul 9, 2024
    • safari

      Public
      Convolutions for Sequence Modeling
      Assembly
      70900251Updated Jun 13, 2024Jun 13, 2024
    • A framework for few-shot evaluation of language models.
      Python
      2.8k1000Updated Jun 8, 2024Jun 8, 2024
    • A framework for few-shot evaluation of language models.
      Python
      2.8k800Updated Jun 3, 2024Jun 3, 2024
    • axolive

      Public
      Go ahead and axolotl questions
      Python
      1.2k200Updated Jun 3, 2024Jun 3, 2024
    • Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
      Jupyter Notebook
      2.6k100Updated Jun 3, 2024Jun 3, 2024