paper7Updated Nov 20, 2026 · Português
← All organizations

Maracatu Labs

location not provided
Small companyruns on device

Language models trained from scratch on Wikipédia pt-BR (17M and 88M); the site is a social oversight/elections portal and does not sell a model.

Models
2
Datasets
1
Downloads in 30 days
179
Followers
2
Likes
3
Smallest model
17M

Releases per quarter

Models and datasets, by creation date on Hugging Face.

2023202420252026

Model licenses

What each model card declares

  • apache-2.02

Dataset licenses

Commercial use under the declared license

  • No license1

Model types

By declared task

  • text-generation2

Where the models run

By file format and size

  • server1
  • device1

Languages

Declared in model and dataset cards

  • pt2

Models on Hugging Face (2)

Only what is published under the organization's Hugging Face account. Products and models under other accounts are not listed here.

ModelTaskRuns onSizeLicenseLikesUpdatedDownloads
maracatu-80mtext-generationserver88Mapache-2.017 months ago43
maracatu-20mtext-generationdevice17Mapache-2.017 months ago67

Datasets (1)

Commercial use reflects only the declared license; an open license does not guarantee that the content owners granted the rights.

DatasetLicenseCommercial useRowsUpdatedDownloads
maracatu-corpus-v2no licenseNo license10M<n<100M7 months ago69

Papers (3)

All papers

From arXiv. 0 by the organization, matched by a model name in the title or by its own authors; 3 only cited in model cards.

  1. Nov 2024
    Tucano: Advancing Neural Text Generation for Portuguese

    Nicholas Kluge Corrêa, Aniket Sen, Sophia Falk, Shiza Fatimah

    arXiv 2411.07854cited only
  2. Mar 2024
    Sabiá-2: A New Generation of Portuguese Large Language Models

    Thales Sales Almeida, Hugo Abonizio, Rodrigo Nogueira, Ramon Pires

    arXiv 2403.09887cited only
  3. Mar 2022
    Training Compute-Optimal Large Language Models

    Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai and 7 more

    arXiv 2203.15556cited only

Declared links

Only what the authors declared in each model card. A missing declaration does not mean there is no use.

Trains on data from
CulturaX (CulturaX); wikimedia (wikipedia)