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

TL;DR

This report presents Amadeus Verbo, a family of large Portuguese language models of various sizes, demonstrating the ease of fine-tuning foundation models to promote open-source development for Brazilian Portuguese.

Contribution

It introduces a versatile family of Portuguese LLMs with multiple sizes and tuning options, emphasizing accessible fine-tuning for democratized development.

Findings

Models are available on HuggingFace for public use.

Demonstrates ease of fine-tuning foundation models for Portuguese.

Supports diverse use cases with different model sizes.

Abstract

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.