amadeusai/Amadeus-Verbo-MI-Qwen-2.5-32B-PT-BR-Instruct-Experimental
The Amadeus-Verbo-MI-Qwen-2.5-32B-PT-BR-Instruct-Experimental model by amadeusai is a 32.8 billion parameter instruction-tuned language model based on the Qwen2.5 architecture, specifically optimized for Portuguese language tasks. This model is a merge of the Qwen/Qwen2.5-32B-Instruct and amadeusai/AV-BI-Qwen2.5-32B-PT-BR-Instruct models, created using the SLERP merge method. It is designed to excel in generating responses and completing tasks in Brazilian Portuguese, leveraging its Qwen2.5 foundation and specialized fine-tuning.
Loading preview...
Model Overview
The Amadeus-Verbo-MI-Qwen-2.5-32B-PT-BR-Instruct-Experimental is a 32.8 billion parameter instruction-tuned language model developed by amadeusai. It is built upon the robust Qwen2.5 architecture and has been specifically optimized for the Portuguese language, particularly Brazilian Portuguese.
Key Characteristics
- Architecture: Based on the Qwen2.5 family of models, known for strong performance across various language tasks.
- Parameter Count: Features 32.8 billion parameters, providing substantial capacity for complex language understanding and generation.
- Multilingual Focus: This model is a merge of a general Qwen2.5-32B-Instruct model and a Portuguese-specific instruction-tuned variant, making it highly proficient in Portuguese.
- Merge Method: Created using the SLERP (Spherical Linear Interpolation) merge method, combining the strengths of its constituent models.
- Context Length: Supports a context length of 32768 tokens, enabling processing of longer inputs and generating more coherent, extended responses.
Primary Use Case
This model is particularly well-suited for applications requiring high-quality text generation, instruction following, and conversational AI in Brazilian Portuguese. Its specialized training makes it an excellent choice for tasks such as content creation, customer support, and educational tools targeting Portuguese-speaking users.