Small open models in Portuguese: TeenyTinyLlama, Tucano, Tucano2; GigaVerbo v2; quality classifiers; 32 models, 24 datasets.
Models and datasets, by creation date on Hugging Face.
What each model card declares
Commercial use under the declared license
By declared task
By file format and size
Declared in model and dataset cards
Only what is published under the organization's Hugging Face account. Products and models under other accounts are not listed here.
| Model | Task | Runs on | Size | License | Likes | Updated | Downloads |
|---|---|---|---|---|---|---|---|
| Tucano2-qwen-1.5B-Instruct | text-generation | server | 1,5B | apache-2.0 | 3 | 3 months ago | 1.3K |
| Tucano2-qwen-1.5B-Think | text-generation | server | 1,5B | apache-2.0 | 1 | 3 months ago | 148 |
| Tucano2-qwen-3.7B-Instruct | text-generation | server | 3,8B | apache-2.0 | 7 | 3 months ago | 1.9K |
| Tucano2-qwen-3.7B-Think | text-generation | server | 3,8B | apache-2.0 | 0 | 3 months ago | 154 |
| GigaKriya-ablation-EDU-1.5B | text-generation | server | 1,5B | apache-2.0 | 0 | 6 months ago | 18 |
| GigaKriya-ablation-NonEDU-1.5B | text-generation | server | 1,5B | apache-2.0 | 0 | 6 months ago | 16 |
| GigaLekh-ablation-EDU-1.5B | text-generation | server | 1,5B | apache-2.0 | 0 | 6 months ago | 14 |
| GigaLekh-ablation-NonEDU-1.5B | text-generation | server | 1,5B | apache-2.0 | 0 | 6 months ago | 15 |
| GigaVerbo-v2-ablation-EDU-1.5B | text-generation | server | 1,5B | apache-2.0 | 0 | 9 months ago | 11 |
| GigaVerbo-v2-ablation-EDU-Synth-1.5B | text-generation | server | 1,5B | apache-2.0 | 0 | 9 months ago | 675 |
| GigaVerbo-v2-ablation-NonEDU-1.5B | text-generation | server | 1,5B | apache-2.0 | 0 | 9 months ago | 10 |
| GigaVerbo-v2-ablation-Synth-1.5B | text-generation | server | 1,5B | apache-2.0 | 0 | 9 months ago | 21 |
| LilMoo-v0.1 | text-generation | server | 670M | apache-2.0 | 0 | 9 months ago | 75 |
| LilMoo-v0.2 | text-generation | server | 670M | apache-2.0 | 0 | 9 months ago | 404 |
| LilTii-v0.1 | text-generation | server | 670M | apache-2.0 | 0 | 9 months ago | 43 |
| LilTii-v0.2 | text-generation | server | 670M | apache-2.0 | 0 | 9 months ago | 242 |
| Tucano2-0.6B-Base | text-generation | server | 670M | apache-2.0 | 1 | 9 months ago | 204 |
| Tucano2-qwen-0.5B-Base | text-generation | server | 491M | apache-2.0 | 0 | 9 months ago | 138 |
| Tucano2-qwen-0.5B-Instruct | text-generation | server | 491M | apache-2.0 | 2 | 9 months ago | 803 |
| Tucano2-qwen-0.5B-Think | text-generation | server | 491M | apache-2.0 | 0 | 9 months ago | 818 |
| Tucano2-qwen-1.5B-Base | text-generation | server | 1,5B | apache-2.0 | 3 | 9 months ago | 834 |
| Tucano2-qwen-3.7B-Base | text-generation | server | 3,8B | apache-2.0 | 1 | 9 months ago | 839 |
| bengali-banglabert-edu-classifier | text-classification | server | 35M | other | 0 | 9 months ago | 21 |
| bengali-banglabert-toxicity-classifier | text-classification | server | 35M | other | 0 | 9 months ago | 90 |
| hindi-roberta-edu-classifier | text-classification | server | 278M | cc | 0 | 9 months ago | 15 |
| hindi-roberta-toxicity-classifier | text-classification | server | 278M | cc | 0 | 9 months ago | 12 |
| portuguese-bertabaporu-large-toxicity-classifier | text-classification | server | 369M | apache-2.0 | 0 | 9 months ago | 15 |
| portuguese-bertimbau-edu-classifier | text-classification | server | 109M | apache-2.0 | 0 | 9 months ago | 13 |
| portuguese-bertimbau-large-edu-classifier | text-classification | server | 334M | apache-2.0 | 0 | 9 months ago | 25 |
| portuguese-bertimbau-toxicity-classifier | text-classification | server | 109M | apache-2.0 | 0 | 9 months ago | 38 |
| portuguese-qwen3-4b-instruct-quality-classifier | text-classification | server | 4B | apache-2.0 | 0 | 9 months ago | 15 |
| portuguese-qwen3-4b-instruct-quality-judge | text-generation | server | 4B | apache-2.0 | 0 | 9 months ago | 19 |
Commercial use reflects only the declared license; an open license does not guarantee that the content owners granted the rights.
| Dataset | License | Commercial use | Rows | Updated | Downloads |
|---|---|---|---|---|---|
| gigaverbo-v2 | other | Check | 375M | 2 months ago | 2.3K |
| gigakriya-v1 | other | Check | 41.6M | 6 months ago | 1.1K |
| gigalekh-v1 | other | Check | 83.6M | 6 months ago | 914 |
| multilingual-personas | other | Check | 52K | 7 months ago | 57 |
| bengali-edu-qwen-annotations | apache-2.0 | Allowed | 320K | 9 months ago | 60 |
| bengali-toxicity-qwen-annotations | apache-2.0 | Allowed | 320K | 9 months ago | 69 |
| gigaverbo-v2-preferences | apache-2.0 | Allowed | 28K | 9 months ago | 183 |
| gigaverbo-v2-sft | apache-2.0 | Allowed | 4.1M | 9 months ago | 707 |
| gigaverbo-v2-synth | no license | No license | 11.2M | 9 months ago | 628 |
| hindi-edu-qwen-annotations | apache-2.0 | Allowed | 400K | 9 months ago | 64 |
| hindi-toxicity-qwen-annotations | apache-2.0 | Allowed | 400K | 9 months ago | 75 |
| portuguese-edu-qwen-annotations | apache-2.0 | Allowed | 700K | 9 months ago | 78 |
| portuguese-eval-logs-olmo2-smollm3 | apache-2.0 | Allowed | 203 | 9 months ago | 65 |
| portuguese-instruct-quality-qwen-annotations | apache-2.0 | Allowed | 500K | 9 months ago | 110 |
| portuguese-toxicity-qwen-annotations | apache-2.0 | Allowed | 700K | 9 months ago | 73 |
| tokenizers | other | Check | 9M | 9 months ago | 636 |
| LAMBADA-poly | mit | Allowed | 31K | 9 months ago | 60 |
| CALAME-PT | mit | Allowed | 2.1K | 9 months ago | 47 |
| IFEval-PT | apache-2.0 | Allowed | 300 | 9 months ago | 66 |
| gsm8k-pt | mit | Allowed | 8.8K | 9 months ago | 209 |
| ARC-poly | cc-by-sa-4.0 | With conditions | 80K | 9 months ago | 163 |
| mc4-50k | no license | No license | 5.4M | 10 months ago | 61 |
| Hellaswag-poly | mit | Allowed | 275K | 1 year ago | 105 |
| MMLU-poly | mit | Allowed | 443K | 1 year ago | 172 |
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.
Nicholas Kluge Corrêa, Aniket Sen, Shiza Fatimah, Sophia Falk, Lennard Landgraf and 2 more
Shiza Fatimah, Aniket Sen, Sophia Falk, Florian Mai, Lucie Flek and 1 more
Nicholas Kluge Corrêa
Ricardo Lopes, João Magalhães, David Semedo
Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu and 3 more
Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun and 7 more
Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Kazi Samin, Md Saiful Islam and 3 more
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang and 4 more
Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, Yejin Choi
Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal and 2 more
Only what the authors declared in each model card. A missing declaration does not mean there is no use.