amadeusai/Amadeus-Verbo-MI-Qwen-2.5-14B-PT-BR-Instruct-Experimental

TEXT GENERATIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 27, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The amadeusai/Amadeus-Verbo-MI-Qwen-2.5-14B-PT-BR-Instruct-Experimental is a 14.8 billion parameter instruction-tuned language model, created by amadeusai, based on the Qwen2.5 architecture. This model is a merge of Qwen/Qwen2.5-14B-Instruct and amadeusai/AV-BI-Qwen2.5-14B-PT-BR-Instruct, utilizing the SLERP merge method. It is specifically optimized for generating responses in Brazilian Portuguese, making it suitable for applications requiring high-quality, localized text generation.

Loading preview...

Model Overview

This model, amadeusai/Amadeus-Verbo-MI-Qwen-2.5-14B-PT-BR-Instruct-Experimental, is a 14.8 billion parameter instruction-tuned language model developed by amadeusai. It is built upon the Qwen2.5 architecture and was created using the MergeKit tool.

Merge Details

The model is a result of merging two base models: Qwen/Qwen2.5-14B-Instruct and amadeusai/AV-BI-Qwen2.5-14B-PT-BR-Instruct. The merge was performed using the SLERP (Spherical Linear Interpolation) method, which combines the weights of the constituent models to create a new, hybrid model. This approach aims to leverage the strengths of both original models.

Key Capabilities

  • Brazilian Portuguese Instruction Following: The model is specifically fine-tuned and optimized for understanding and generating text in Brazilian Portuguese, making it highly effective for localized applications.
  • Text Generation: Capable of generating coherent and contextually relevant text based on given prompts, as demonstrated by the provided examples for nutritional planning.
  • Qwen2.5 Architecture: Benefits from the robust capabilities of the Qwen2.5 family of models, known for strong performance in various language tasks.

Recommended Use Cases

This model is particularly well-suited for:

  • Applications requiring high-quality text generation in Brazilian Portuguese.
  • Instruction-following tasks where the input and desired output are in Portuguese.
  • Developing chatbots, content creation tools, or virtual assistants targeting Portuguese-speaking users.

For optimal performance, it is recommended to use the latest version of the Hugging Face Transformers library.

Finetunes
1 models