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

Hugging Face
TEXT GENERATIONPricing:Input $12 / Output $20Concurrent Unit Cost:4Model Size:72.7BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 28, 2025Architecture:Transformer Featherless Exclusive Warm

The amadeusai/Amadeus-Verbo-MI-Qwen-2.5-72B-PT-BR-Instruct-Experimental is a 72.7 billion parameter instruction-tuned language model based on the Qwen2.5 architecture. Developed by amadeusai, this model is a merge of the Qwen/Qwen2.5-72B-Instruct and amadeusai/AV-BI-Qwen2.5-72B-PT-BR-Instruct, specifically optimized for performance in Portuguese. It is designed for general text generation and instruction-following tasks, particularly excelling in scenarios requiring strong Portuguese language capabilities.

Loading preview...

Model Overview

This model, Amadeus-Verbo-MI-Qwen-2.5-72B-PT-BR-Instruct-Experimental, is a 72.7 billion parameter instruction-tuned language model built upon the Qwen2.5 architecture. It was created by amadeusai using the mergekit tool, specifically employing the SLERP merge method.

Key Capabilities

  • Portuguese Language Optimization: This model is a merge of a base Qwen2.5-72B-Instruct model and a Portuguese-instructed variant, suggesting enhanced performance and fluency in Portuguese.
  • Instruction Following: Designed to respond to instructions effectively, making it suitable for various conversational and task-oriented applications.
  • Text Generation: Capable of generating coherent and contextually relevant text based on given prompts.

Merge Details

The model integrates two primary components:

  • Qwen/Qwen2.5-72B-Instruct
  • amadeusai/AV-BI-Qwen2.5-72B-PT-BR-Instruct
    The merge configuration utilized a SLERP method with specific parameter weighting for self-attention and MLP layers, aiming to combine the strengths of both merged models. The model operates with bfloat16 precision.

When to Use This Model

  • Portuguese-centric Applications: Ideal for use cases where high-quality text generation and instruction following in Portuguese are critical.
  • General Instruction Following: Suitable for a wide range of tasks requiring the model to understand and execute user commands.
  • Research and Experimentation: As an "Experimental" model, it's well-suited for developers and researchers exploring advanced LLM capabilities, particularly in a multilingual context focusing on Portuguese.

Finetunes
1 models