Skip to content
@epfl-dlab

EPFL Data Science & AI Lab (dlab)

Popular repositories Loading

  1. aiflows aiflows Public

    🤖🌊 aiFlows: The building blocks of your collaborative AI

    Jupyter Notebook 275 13

  2. transformers-CFG transformers-CFG Public

    🤗 A specialized library for integrating context-free grammars (CFG) in EBNF with the Hugging Face Transformers

    Python 139 23

  3. GoogleTrendsAnchorBank GoogleTrendsAnchorBank Public

    Google Trends, made easy.

    HTML 123 25

  4. GenIE GenIE Public

    The autoregressive information extraction system GenIE (Generative Information Extraction) implemented in PyTorch.

    Python 104 9

  5. llm-latent-language llm-latent-language Public

    Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".

    Jupyter Notebook 88 20

  6. SynthIE SynthIE Public

    The data and the PyTorch implementation for the models and experiments in the paper "Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction".

    Python 63 5

Repositories

Showing 10 of 116 repositories
  • epfl-dlab/model-raising-data's past year of commit activity
    Python 1 3 0 0 Updated Sep 14, 2026
  • pretraining_persona Public

    Tracing Persona Vectors Through LLM Pretraining

    epfl-dlab/pretraining_persona's past year of commit activity
    Python 8 Apache-2.0 0 0 0 Updated Sep 14, 2026
  • nelight Public
    epfl-dlab/nelight's past year of commit activity
    Python 3 MIT 1 0 0 Updated Aug 17, 2026
  • spp Public

    Synthetic Persona Pretraining (SPP): Alignment from Token Zero — umbrella repo for spp-data, spp-training, spp-evals

    epfl-dlab/spp's past year of commit activity
    5 MIT 1 0 0 Updated Aug 14, 2026
  • spp-evals Public

    Evaluation harness for Synthetic Persona Pretraining (SPP): constitution adherence, value prioritization, jailbreak robustness, over-refusal, and capabilities

    epfl-dlab/spp-evals's past year of commit activity
    Python 0 Apache-2.0 0 0 0 Updated Aug 14, 2026
  • spp-training Public

    Training pipeline for Synthetic Persona Pretraining (SPP): Megatron pretraining of the five paper variants and the shared SP-SFT post-training recipe

    epfl-dlab/spp-training's past year of commit activity
    Python 0 Apache-2.0 0 0 0 Updated Aug 14, 2026
  • spp-data Public

    Data-generation pipeline for Synthetic Persona Pretraining (SPP)

    epfl-dlab/spp-data's past year of commit activity
    Python 0 MIT 0 0 0 Updated Aug 14, 2026
  • zip2zip Public
    epfl-dlab/zip2zip's past year of commit activity
    Python 19 Apache-2.0 6 2 0 Updated Aug 12, 2026
  • epfl-dlab/zip2zip-compression's past year of commit activity
    Rust 2 MIT 2 1 0 Updated Jul 10, 2026
  • epfl-dlab/model-raising-chat's past year of commit activity
    Python 0 0 0 0 Updated Apr 18, 2026

Top languages

Loading…

Most used topics

Loading…