Metraipolis › archive › dc_fc7803b73cc0
Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese — arXiv:2610.40533
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40533
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:17:10.002Z
- SHA-256 of the archived text
a5f8c39bd6f8cb7c12b8c9a684377d51223c83050fd106245fd0ff771f3677d9- Stable URL of this page
https://metraipolis.com/documento/dc_fc7803b73cc0
How to cite
Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese — arXiv:2610.40533 — arXiv (en), https://arxiv.org/abs/2610.40533 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc7803b73cc0 (Metraipolis archive dc_fc7803b73cc0, sha256 a5f8c39bd6f8cb7c12b8c9a684377d51223c83050fd106245fd0ff771f3677d9)
BibTeX
@misc{dcfc7803b73cc0,
title = {Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese — arXiv:2610.40533},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40533},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc7803b73cc0; sha256 a5f8c39bd6f8cb7c12b8c9a684377d51223c83050fd106245fd0ff771f3677d9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40533. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It proposes no new method. It releases a tested Python package and two notebooks in Brazilian Portuguese with autoregressive and masked diffusion generation on one network, a preregistered comparison protocol, legal tasks built from text alone with a Kneser-Ney floor and public yardsticks, reference numbers for models of 11 to 12M parameters, and a catalogue of defects that only measurement revealed. On Brazilian prose and federal laws, at minutes per run, the autoregressive mode peaks at 64 epochs over the same text and then memorises it, while masked diffusion improves up to 256. At their best points on test, the diffusion bound exceeds the autoregressive likelihood by 0.06 bits per byte, within the preregistered minimum effect. On held-out laws and on acts published after training, the model ties a 6-gram floor in likelihood on the same windows, and it loses to the floor at continuing those acts. It beats the floor at detecting tampered text, and fills cross-references more often than the floor and public models of 160M and 630M parameters, only in decrees, a genre absent from training, where those scorers stay near or below chance, and in filling the blank only when each group weighs the same, since per item it ties the 630M model. On laws, the public models, trained with about 5x10^2 to 10^5 times its compute, lead in tampered text and continuation. The blind human reading is preregistered and not part of this version. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.40533 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T06:07:23.378Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).