amadeusai/Amadeus-Verbo-FI-Qwen2.5-72B-PT-BR-Instruct

TEXT GENERATIONPricing:Input $12 / Output $20Concurrent Unit Cost:4Model Size:72.7BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 28, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Amadeus-Verbo-FI-Qwen2.5-72B-PT-BR-Instruct is a 72.7 billion parameter Brazilian-Portuguese language model developed by amadeusai. Fine-tuned from the Qwen2.5-72B-Instruct base model over two epochs with a 600k instruction dataset, it is specifically optimized for generating content in Brazilian Portuguese. This Transformer-based model features a substantial context length of 133,072 tokens, making it suitable for complex and lengthy Portuguese text generation tasks.

Loading preview...

Amadeus-Verbo-FI-Qwen2.5-72B-PT-BR-Instruct Overview

Amadeus-Verbo-FI-Qwen2.5-72B-PT-BR-Instruct is a large language model specifically designed for Brazilian Portuguese (PT-BR). Developed by amadeusai, this model is a fine-tuned version of the robust Qwen2.5-72B-Instruct base model.

Key Characteristics

  • Architecture: Built on a Transformer architecture, incorporating features like RoPE, SwiGLU, RMSNorm, and Attention QKV bias.
  • Parameters: It boasts 72.7 billion parameters, with 70.0 billion non-embedding parameters, making it a powerful model for complex tasks.
  • Context Length: Features an extensive context window of 133,072 tokens, enabling it to process and generate very long sequences of text.
  • Training: Fine-tuned for two epochs using a substantial 600,000 instruction dataset, enhancing its ability to follow instructions in Portuguese.
  • Language Focus: Exclusively developed and optimized for Brazilian Portuguese, ensuring high-quality and culturally relevant outputs in this language.

Use Cases

This model is ideal for applications requiring advanced language understanding and generation in Brazilian Portuguese, such as:

  • Content creation: Generating articles, reports, or creative writing in PT-BR.
  • Instruction following: Responding to complex prompts and instructions in Portuguese.
  • Long-form text processing: Handling and generating extensive documents or conversations due to its large context window.

For more technical details, refer to the associated research article: Amadeus-Verbo Technical Report.

Finetunes
1 models