Amadeus-Verbo Technical Report: The powerful Qwen2.5 family models trained in Portuguese

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cruz-Castañeda, William Alberto, Amadeus, Marcellus
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916770248392704
author Cruz-Castañeda, William Alberto
Amadeus, Marcellus
author_facet Cruz-Castañeda, William Alberto
Amadeus, Marcellus
contents This report introduces the experience of developing Amadeus Verbo, a family of large language models for Brazilian Portuguese. To handle diverse use cases, Amadeus Verbo includes base-tuned, merged, and instruction-tuned models in sizes of 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B parameters. Thus, the main objective is to show how easy it is to fine-tune foundation models to democratize the open-source development of Brazilian Portuguese LLMs when data and resources are available. Amadeus-Verbo family models are all available at HuggingFace at https://huggingface.co/collections/amadeusai/amadeus-verbo-qwen25-67cf2e7aae69ce2b3bcdcfda.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00019
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Amadeus-Verbo Technical Report: The powerful Qwen2.5 family models trained in Portuguese
Cruz-Castañeda, William Alberto
Amadeus, Marcellus
Computation and Language
Artificial Intelligence
This report introduces the experience of developing Amadeus Verbo, a family of large language models for Brazilian Portuguese. To handle diverse use cases, Amadeus Verbo includes base-tuned, merged, and instruction-tuned models in sizes of 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B parameters. Thus, the main objective is to show how easy it is to fine-tune foundation models to democratize the open-source development of Brazilian Portuguese LLMs when data and resources are available. Amadeus-Verbo family models are all available at HuggingFace at https://huggingface.co/collections/amadeusai/amadeus-verbo-qwen25-67cf2e7aae69ce2b3bcdcfda.
title Amadeus-Verbo Technical Report: The powerful Qwen2.5 family models trained in Portuguese
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.00019