paper7Updated Nov 20, 2026 · Português
← All organizations

Polygl0t

location not provided

Small open models in Portuguese: TeenyTinyLlama, Tucano, Tucano2; GigaVerbo v2; quality classifiers; 32 models, 24 datasets.

Models
32
Datasets
24
Downloads in 30 days
17K
Followers
50
Likes
29
Papers
3
Smallest model
35M

Releases per quarter

Models and datasets, by creation date on Hugging Face.

2023202420252026

Model licenses

What each model card declares

  • apache-2.028
  • other2
  • cc2

Dataset licenses

Commercial use under the declared license

  • Allowed16
  • Check5
  • No license2
  • With conditions1

Model types

By declared task

  • text-generation23
  • text-classification9

Where the models run

By file format and size

  • server32

Languages

Declared in model and dataset cards

  • pt33
  • bn13
  • hi10
  • de5
  • es5
  • en4

Models on Hugging Face (32)

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

ModelTaskRuns onSizeLicenseLikesUpdatedDownloads
Tucano2-qwen-1.5B-Instructtext-generationserver1,5Bapache-2.033 months ago1.3K
Tucano2-qwen-1.5B-Thinktext-generationserver1,5Bapache-2.013 months ago148
Tucano2-qwen-3.7B-Instructtext-generationserver3,8Bapache-2.073 months ago1.9K
Tucano2-qwen-3.7B-Thinktext-generationserver3,8Bapache-2.003 months ago154
GigaKriya-ablation-EDU-1.5Btext-generationserver1,5Bapache-2.006 months ago18
GigaKriya-ablation-NonEDU-1.5Btext-generationserver1,5Bapache-2.006 months ago16
GigaLekh-ablation-EDU-1.5Btext-generationserver1,5Bapache-2.006 months ago14
GigaLekh-ablation-NonEDU-1.5Btext-generationserver1,5Bapache-2.006 months ago15
GigaVerbo-v2-ablation-EDU-1.5Btext-generationserver1,5Bapache-2.009 months ago11
GigaVerbo-v2-ablation-EDU-Synth-1.5Btext-generationserver1,5Bapache-2.009 months ago675
GigaVerbo-v2-ablation-NonEDU-1.5Btext-generationserver1,5Bapache-2.009 months ago10
GigaVerbo-v2-ablation-Synth-1.5Btext-generationserver1,5Bapache-2.009 months ago21
LilMoo-v0.1text-generationserver670Mapache-2.009 months ago75
LilMoo-v0.2text-generationserver670Mapache-2.009 months ago404
LilTii-v0.1text-generationserver670Mapache-2.009 months ago43
LilTii-v0.2text-generationserver670Mapache-2.009 months ago242
Tucano2-0.6B-Basetext-generationserver670Mapache-2.019 months ago204
Tucano2-qwen-0.5B-Basetext-generationserver491Mapache-2.009 months ago138
Tucano2-qwen-0.5B-Instructtext-generationserver491Mapache-2.029 months ago803
Tucano2-qwen-0.5B-Thinktext-generationserver491Mapache-2.009 months ago818
Tucano2-qwen-1.5B-Basetext-generationserver1,5Bapache-2.039 months ago834
Tucano2-qwen-3.7B-Basetext-generationserver3,8Bapache-2.019 months ago839
bengali-banglabert-edu-classifiertext-classificationserver35Mother09 months ago21
bengali-banglabert-toxicity-classifiertext-classificationserver35Mother09 months ago90
hindi-roberta-edu-classifiertext-classificationserver278Mcc09 months ago15
hindi-roberta-toxicity-classifiertext-classificationserver278Mcc09 months ago12
portuguese-bertabaporu-large-toxicity-classifiertext-classificationserver369Mapache-2.009 months ago15
portuguese-bertimbau-edu-classifiertext-classificationserver109Mapache-2.009 months ago13
portuguese-bertimbau-large-edu-classifiertext-classificationserver334Mapache-2.009 months ago25
portuguese-bertimbau-toxicity-classifiertext-classificationserver109Mapache-2.009 months ago38
portuguese-qwen3-4b-instruct-quality-classifiertext-classificationserver4Bapache-2.009 months ago15
portuguese-qwen3-4b-instruct-quality-judgetext-generationserver4Bapache-2.009 months ago19

Datasets (24)

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

DatasetLicenseCommercial useRowsUpdatedDownloads
gigaverbo-v2otherCheck375M2 months ago2.3K
gigakriya-v1otherCheck41.6M6 months ago1.1K
gigalekh-v1otherCheck83.6M6 months ago914
multilingual-personasotherCheck52K7 months ago57
bengali-edu-qwen-annotationsapache-2.0Allowed320K9 months ago60
bengali-toxicity-qwen-annotationsapache-2.0Allowed320K9 months ago69
gigaverbo-v2-preferencesapache-2.0Allowed28K9 months ago183
gigaverbo-v2-sftapache-2.0Allowed4.1M9 months ago707
gigaverbo-v2-synthno licenseNo license11.2M9 months ago628
hindi-edu-qwen-annotationsapache-2.0Allowed400K9 months ago64
hindi-toxicity-qwen-annotationsapache-2.0Allowed400K9 months ago75
portuguese-edu-qwen-annotationsapache-2.0Allowed700K9 months ago78
portuguese-eval-logs-olmo2-smollm3apache-2.0Allowed2039 months ago65
portuguese-instruct-quality-qwen-annotationsapache-2.0Allowed500K9 months ago110
portuguese-toxicity-qwen-annotationsapache-2.0Allowed700K9 months ago73
tokenizersotherCheck9M9 months ago636
LAMBADA-polymitAllowed31K9 months ago60
CALAME-PTmitAllowed2.1K9 months ago47
IFEval-PTapache-2.0Allowed3009 months ago66
gsm8k-ptmitAllowed8.8K9 months ago209
ARC-polycc-by-sa-4.0With conditions80K9 months ago163
mc4-50kno licenseNo license5.4M10 months ago61
Hellaswag-polymitAllowed275K1 year ago105
MMLU-polymitAllowed443K1 year ago172

Papers (10)

All papers

From arXiv. 3 by the organization, matched by a model name in the title or by its own authors; 7 only cited in model cards.

  1. Mar 2026
    Tucano 2 Cool: Better Open Source LLMs for Portuguese

    Nicholas Kluge Corrêa, Aniket Sen, Shiza Fatimah, Sophia Falk, Lennard Landgraf and 2 more

    arXiv 2603.03543
  2. Mar 2026
    Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi

    Shiza Fatimah, Aniket Sen, Sophia Falk, Florian Mai, Lucie Flek and 1 more

    arXiv 2603.03508
  3. Jun 2024
  4. Feb 2024
    GlórIA -- A Generative and Open Large Language Model for Portuguese

    Ricardo Lopes, João Magalhães, David Semedo

    arXiv 2402.12969cited only
  5. Nov 2023
    Instruction-Following Evaluation for Large Language Models

    Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu and 3 more

    arXiv 2311.07911cited only
  6. Oct 2021
    Training Verifiers to Solve Math Word Problems

    Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun and 7 more

    arXiv 2110.14168cited only
  7. Jan 2021
    BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla

    Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Kazi Samin, Md Saiful Islam and 3 more

    arXiv 2101.00204cited only
  8. Oct 2019
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

    Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang and 4 more

    arXiv 1910.10683cited only
  9. May 2019
    HellaSwag: Can a Machine Really Finish Your Sentence?

    Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, Yejin Choi

    arXiv 1905.07830cited only
  10. Mar 2018
    Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

    Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal and 2 more

    arXiv 1803.05457cited 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
the organization itself (gigaverbo-v2-preferences, gigaverbo-v2-sft, gigakriya-v1 and 10 more); HuggingFaceTB (finemath, smollm-corpus); allenai (big-reasoning-traces, math-meta-reasoning-filtered); HuggingFaceFW (fineweb-edu); nvidia (OpenScience)
Builds on models from
Qwen (Qwen3-0.6B-Base, Qwen3-1.7B-Base, Qwen3-4B-Base and 1 more); the organization itself (Tucano2-qwen-1.5B-Base, Tucano2-qwen-3.7B-Base, Tucano2-qwen-0.5B-Base); NeuralMind (bert-base-portuguese-cased, bert-large-portuguese-cased); csebuetnlp (banglabert_generator); l3cube-pune (hindi-roberta); pablocosta (bertabaporu-large-uncased)
Used by
Mangaba AI (gigaverbo-v2, gigaverbo-v2-synth)