Skip to content
@C4AI

C4AI - Center for Artificial Intelligence

A research center for advanced artificial intelligence in Brazil. Based at the Universidade de São Paulo, sponsored by IBM and FAPESP.

Popular repositories Loading

  1. gap-text2sql gap-text2sql Public

    Forked from awslabs/gap-text2sql

    GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

    Python 31 4

  2. Pira Pira Public

    Pirá: A Bilingual Portuguese-English Dataset for Question-Answering about the Ocean

    Jupyter Notebook 11 4

  3. ArGPT ArGPT Public

    ArGPT: A LLM-based dataset for Argumentation

    Jupyter Notebook 9

  4. token-counter token-counter Public

    Python library + CLI for token counting and token distribution analysis in text datasets for LLM data workflows.

    Python 8 1

  5. arandu_user_guide arandu_user_guide Public

    7 2

  6. PINN_for_Burgers PINN_for_Burgers Public

    Python 5 1

Repositories

Showing 10 of 53 repositories
  • token-counter Public

    Python library + CLI for token counting and token distribution analysis in text datasets for LLM data workflows.

    C4AI/token-counter's past year of commit activity
    Python 8 MIT 1 2 0 Updated Oct 2, 2026
  • blabinha-robios Public Forked from caio-bernardo/blabinha-robios

    Interface Robios para o agente Blabinha

    C4AI/blabinha-robios's past year of commit activity
    Java 1 GPL-3.0 1 0 0 Updated Sep 10, 2026
  • Blabinha-API Public Forked from caio-bernardo/Blabinha-API

    API do agente conversacional Blabinha

    C4AI/Blabinha-API's past year of commit activity
    Python 1 MIT 2 0 0 Updated Sep 10, 2026
  • large-language-models-for-portuguese Public

    A list of large language models trained for the Portuguese language.

    C4AI/large-language-models-for-portuguese's past year of commit activity
    CSS 2 Apache-2.0 2 0 1 Updated May 11, 2026
  • HarpIA_Survey Public
    C4AI/HarpIA_Survey's past year of commit activity
    PHP 3 GPL-3.0 0 0 0 Updated May 5, 2026
  • corpuslab-eda Public

    Corpuslab é uma plataforma Python para análise exploratória de dados e curadoria de corpora portugueses, focada na preparação de conjuntos de dados de alta qualidade para o pré-treinamento de modelos LLMs.

    C4AI/corpuslab-eda's past year of commit activity
    Python 0 0 0 0 Updated Apr 28, 2026
  • tokenweaver Public

    Library to format Hugging Face datasets into fixed-length token sequences tailored to hardware constraints.

    C4AI/tokenweaver's past year of commit activity
    Python 0 0 0 0 Updated Apr 10, 2026
  • Prolind_writing-assistant Public
    C4AI/Prolind_writing-assistant's past year of commit activity
    TypeScript 0 1 0 0 Updated Mar 4, 2026
  • moodle-datafield_harpiainteraction Public

    A Moodle plugin that implements an interaction with a language model for Database activities.

    C4AI/moodle-datafield_harpiainteraction's past year of commit activity
    PHP 1 GPL-3.0 0 0 0 Updated Sep 24, 2025
  • llm_component_relation_classification Public

    Presents an Assesment of Component Classification using LLMs

    C4AI/llm_component_relation_classification's past year of commit activity
    Jupyter Notebook 1 0 0 0 Updated Sep 11, 2025
View all repositories

Top languages

Loading…

Most used topics

Loading…