Skip to content

@Pleias Pleias

Change the repository type filter

All

    Repositories list

    15 repositories

    • pleias_ScholasticAI

      Public
      Python
      •1•33•3•1•Updated Jan 5, 2025Jan 5, 2025

    • BSF_AI_tutor

      Public
      Project provides an API for correcting mistakes in written essays using AI model
      Python
      •0•1•0•0•Updated Dec 20, 2024Dec 20, 2024

    • RAG-Eval

      Public
      R
      •0•0•0•0•Updated Dec 18, 2024Dec 18, 2024

    • nanotron-pleias

      Public
      Minimalistic large language model 3D-parallelism training
      Python
      •
      Apache License 2.0
      •135•0•0•0•Updated Dec 16, 2024Dec 16, 2024

    • Quest-Best-Tokens

      Public
      An introduction to LLM Sampling
      Jupyter Notebook
      •
      MIT License
      •2•74•0•0•Updated Dec 15, 2024Dec 15, 2024

    • Knowledge-LLM

      Public
      Jupyter Notebook
      •
      Apache License 2.0
      •0•3•0•0•Updated Dec 12, 2024Dec 12, 2024

    • language_adherence_tests

      Public
      Testing language adherence of models, i.e. how much they are able to continue the generation in the desired output language.
      R
      •
      Apache License 2.0
      •0•0•0•0•Updated Dec 5, 2024Dec 5, 2024

    • logos

      Public
      0•0•0•0•Updated Dec 4, 2024Dec 4, 2024

    • toxic-commons

      Public
      The official repository for Toxic Commons and Celadon. Toxicity Classification for public domain data.
      Python
      •
      MIT License
      •1•12•1•0•Updated Nov 10, 2024Nov 10, 2024

    • nanotron-tractoai

      Public
      Adaptation of nanotron to run on tractoai
      Python
      •
      Apache License 2.0
      •135•0•0•2•Updated Oct 28, 2024Oct 28, 2024

    • synthetic-ocr

      Public
      Set of scripts to generate synthetic correction/rewriting of problematic OCR
      0•1•0•0•Updated Apr 12, 2024Apr 12, 2024

    • Various-Finetuning

      Public
      Set of scripts to finetune LLMs
      Python
      •2•36•0•0•Updated Mar 30, 2024Mar 30, 2024

    • marginalia

      Public
      Jupyter Notebook
      •
      MIT License
      •5•68•4•0•Updated Mar 4, 2024Mar 4, 2024

    • OCRoscope

      Public
      Small python package to measure OCR quality and other related metrics.
      Python
      •
      MIT License
      •2•21•1•0•Updated Feb 19, 2024Feb 19, 2024

    • marginalia.github.io

      Public
      MIT License
      •0•0•0•0•Updated Feb 18, 2024Feb 18, 2024