Skip to content
@epfml

EPFL Machine Learning and Optimization Laboratory

Popular repositories Loading

  1. ML_course ML_course Public

    EPFL Machine Learning Course, Fall 2024

    Jupyter Notebook 1.3k 908

  2. sent2vec sent2vec Public

    General purpose unsupervised sentence representations

    C++ 1.2k 256

  3. OptML_course OptML_course Public

    EPFL Course - Optimization for Machine Learning - CS-439

    Jupyter Notebook 1.1k 312

  4. attention-cnn attention-cnn Public

    Source code for "On the Relationship between Self-Attention and Convolutional Layers"

    Python 1.1k 127

  5. landmark-attention landmark-attention Public

    Landmark Attention: Random-Access Infinite Context Length for Transformers

    Python 414 36

  6. federated-learning-public-code federated-learning-public-code Public

    Python 154 47

Repositories

Showing 10 of 59 repositories
  • disco Public

    DISCO is a code-free and installation-free browser platform that allows any non-technical user to collaboratively train machine learning models without sharing any private data.

    epfml/disco’s past year of commit activity
    TypeScript 152 Apache-2.0 26 54 6 Updated Oct 28, 2024
  • llm-baselines Public

    NanoGPT-like codebase for LLM training

    epfml/llm-baselines’s past year of commit activity
    Python 69 MIT 21 3 4 Updated Oct 24, 2024
  • prefixlm Public
    epfml/prefixlm’s past year of commit activity
    Python 1 MIT 0 0 0 Updated Oct 23, 2024
  • epfml/getting-started’s past year of commit activity
    Python 15 11 0 3 Updated Oct 23, 2024
  • ML_course Public

    EPFL Machine Learning Course, Fall 2024

    epfml/ML_course’s past year of commit activity
    Jupyter Notebook 1,257 907 3 1 Updated Oct 23, 2024
  • CoBo Public
    epfml/CoBo’s past year of commit activity
    Python 0 0 0 0 Updated Oct 22, 2024
  • epfml/schedules-and-scaling’s past year of commit activity
    Python 50 MIT 2 0 0 Updated Oct 4, 2024
  • CoMiGS Public
    epfml/CoMiGS’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Oct 2, 2024
  • powersgd Public

    Practical low-rank gradient compression for distributed optimization: https://arxiv.org/abs/1905.13727

    epfml/powersgd’s past year of commit activity
    Python 142 MIT 32 1 2 Updated Sep 3, 2024
  • personalized-collaborative-llms Public

    Exploration on-device self-supervised collaborative fine-tuning of large language models with limited local data availability, using Low-Rank Adaptation (LoRA). We introduce three distinct trust-weighted gradient aggregation schemes: weight similarity-based, prediction similarity-based and validation performance-based.

    epfml/personalized-collaborative-llms’s past year of commit activity
    Python 2 Apache-2.0 0 1 0 Updated Sep 2, 2024