amadeusai/Amadeus-Verbo-BI-Qwen-2.5-72B-PT-BR-Instruct-Experimental

TEXT GENERATIONPricing:Input $12 / Output $20Concurrent Unit Cost:4Model Size:72.7BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 19, 2025License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Amadeus-Verbo-BI-Qwen-2.5-72B-PT-BR-Instruct-Experimental is a 72.7 billion parameter Brazilian Portuguese (PT-BR) language model developed by amadeusai. Fine-tuned from the Qwen2.5-72B base model over 2 epochs with 600k instructions, it features a Transformer architecture with a 131,072 token context length. This model is specifically optimized for generating high-quality text in Brazilian Portuguese, making it suitable for applications requiring nuanced language understanding and generation in this specific locale.

Loading preview...

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

This model, developed by amadeusai, is a large language model (LLM) specifically fine-tuned for Brazilian Portuguese (PT-BR). It is based on the powerful Qwen2.5-72B architecture, featuring 72.7 billion parameters and an extensive context length of 131,072 tokens.

Key Capabilities & Features

  • Brazilian Portuguese Specialization: Developed through fine-tuning on a 600k instruction dataset over 2 epochs, making it highly proficient in PT-BR.
  • Robust Architecture: Utilizes a Transformer-based design incorporating RoPE, SwiGLU, RMSNorm, and Attention QKV bias.
  • Large Scale: With 72.7 billion parameters and 80 layers, it offers significant generative capacity.
  • Extended Context Window: Supports a context length of 131,072 tokens, enabling processing of longer inputs and generating more coherent, extended responses.

Use Cases

This model is particularly well-suited for applications requiring deep understanding and generation of text in Brazilian Portuguese. Potential use cases include:

  • Content Generation: Creating articles, reports, marketing copy, or creative writing in PT-BR.
  • Chatbots and Virtual Assistants: Developing conversational AI agents that interact naturally in Brazilian Portuguese.
  • Language Translation & Localization: Enhancing translation quality and localizing content for the Brazilian market.
  • Information Extraction & Summarization: Processing and summarizing PT-BR documents.

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

Finetunes
1 models