amadeusai/Amadeus-Verbo-MI-Qwen-2.5-7B-PT-BR-Instruct-Experimental

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 27, 2025License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Amadeus-Verbo-MI-Qwen-2.5-7B-PT-BR-Instruct-Experimental is a 7.6 billion parameter instruction-tuned language model developed by amadeusai, built upon the Qwen2.5 architecture. This model is a merge of the Qwen/Qwen2.5-7B-Instruct and amadeusai/AV-BI-Qwen2.5-7B-PT-BR-Instruct models, specifically optimized for Portuguese language instruction following. With a context length of 32768 tokens, it excels in generating responses for fitness and Mediterranean diet planning, demonstrating strong performance in domain-specific Portuguese tasks.

Loading preview...

Amadeus-Verbo-MI-Qwen-2.5-7B-PT-BR-Instruct-Experimental Overview

This model, developed by amadeusai, is a 7.6 billion parameter instruction-tuned language model based on the Qwen2.5 architecture. It was created using the SLERP merge method, combining the capabilities of the base Qwen/Qwen2.5-7B-Instruct model with amadeusai/AV-BI-Qwen2.5-7B-PT-BR-Instruct. This strategic merge aims to enhance its performance, particularly for instruction-following tasks in Portuguese.

Key Capabilities

  • Portuguese Language Optimization: Specifically fine-tuned and merged to improve understanding and generation in Brazilian Portuguese.
  • Instruction Following: Designed to accurately follow user instructions and generate relevant responses.
  • Domain-Specific Applications: Demonstrated proficiency in generating detailed content for areas like nutritional planning (e.g., fitness and Mediterranean diets).
  • Qwen2.5 Foundation: Benefits from the robust architecture and capabilities of the Qwen2.5 model family.

When to Use This Model

This model is particularly well-suited for applications requiring:

  • Portuguese-centric AI Assistants: Ideal for chatbots or virtual assistants operating primarily in Portuguese.
  • Content Generation in Portuguese: Generating text, summaries, or creative content in Portuguese.
  • Specialized Instruction Following: Tasks that benefit from a model optimized for specific instructions, especially within the Portuguese language context.
  • Research and Development: As an experimental merge, it offers a valuable resource for exploring advanced Portuguese NLP applications.

Finetunes
1 models