Skip to content

Welcome to the OpenLLM-France 🇫🇷 Github

Discord

The aim of the OpenLLM France community is to collaborate on the development of truly Open Source AI LLM models.

This space contains the software tools used to :

  • collect and clean data;
  • pretrain the foundation models;
  • train and align the instruction models.

This space is strongly linked with the following Hugging Face space that contains and details datasets and models :

According to the OSI, open source AI model means that we provide :

  • the training corpus under an open license --> Hugging Face;
  • model weights under an open source non-restrictive license --> Hugging Face;
  • code for data curation and training algorithms under open source licenses --> this Github space.

Follow us:

Pinned Loading

  1. Manifesto Manifesto Public

    Page de préconfiguration de la communauté OpenLLM-France

    53 1

  2. Lucie-dataset-filtering Lucie-dataset-filtering Public

    Lucie-dataset-filtering: Code to compile and preprocess training data for Lucie's training

    Python 2 1

  3. Lucie-Training Lucie-Training Public

    Code for continual pretraining of LUCIE

    Jupyter Notebook 53 8

  4. wikiplaintext wikiplaintext Public

    Get plain text from Wikipedia pages

    HTML 11

Repositories

Showing 10 of 23 repositories
  • lighteval Public Forked from huggingface/lighteval

    Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

    OpenLLM-France/lighteval's past year of commit activity
    Python 0 MIT 564 0 3 Updated Sep 17, 2026
  • AudioBench Public Forked from AudioLLMs/AudioBench

    AudioBench: A Universal Benchmark for Audio Large Language Models

    OpenLLM-France/AudioBench's past year of commit activity
    Python 0 18 0 0 Updated Sep 9, 2026
  • OpenLLM-France/Luciole-Training's past year of commit activity
    Python 14 GPL-3.0 1 1 0 Updated Sep 8, 2026
  • gorilla Public Forked from ShishirPatil/gorilla

    Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

    OpenLLM-France/gorilla's past year of commit activity
    Python 0 Apache-2.0 1,490 0 0 Updated Sep 7, 2026
  • RL Public Forked from NVIDIA-NeMo/RL

    Scalable toolkit for efficient model reinforcement

    OpenLLM-France/RL's past year of commit activity
    Python 0 Apache-2.0 569 0 0 Updated Sep 4, 2026
  • llama.cpp Public Forked from ggml-org/llama.cpp

    LLM inference in C/C++

    OpenLLM-France/llama.cpp's past year of commit activity
    C++ 0 MIT 24,032 0 1 Updated Aug 18, 2026
  • datatrove Public Forked from huggingface/datatrove

    Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

    OpenLLM-France/datatrove's past year of commit activity
    Python 0 Apache-2.0 309 0 0 Updated Jul 31, 2026
  • dcp Public

    Data collection platform

    OpenLLM-France/dcp's past year of commit activity
    Python 0 AGPL-3.0 0 1 4 Updated Jun 10, 2026
  • Lucie-Training Public

    Code for continual pretraining of LUCIE

    OpenLLM-France/Lucie-Training's past year of commit activity
    Jupyter Notebook 53 GPL-3.0 8 0 1 Updated Jun 2, 2026
  • OpenLLM-France/AudioBenchResults's past year of commit activity
    HTML 0 0 0 0 Updated Apr 17, 2026

Top languages

Loading…

Most used topics

Loading…