amadeusai/Amadeus-Verbo-BI-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:Nov 28, 2024License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Amadeus-Verbo-BI-Qwen2.5-7B-PT-BR-Instruct is a 7.62 billion parameter Brazilian-Portuguese language model developed by amadeusai, fine-tuned from the Qwen2.5-7B base model. This Transformer-based model is specifically optimized for instruction-following tasks in Brazilian Portuguese, leveraging a 600k instruction dataset over two epochs. It features a 131,072-token context length and is designed for generating high-quality text responses in its target language.

Loading preview...

Amadeus-Verbo-BI-Qwen2.5-7B-PT-BR-Instruct Overview

Amadeus-Verbo-BI-Qwen2.5-7B-PT-BR-Instruct is a specialized Brazilian-Portuguese Large Language Model (PT-BR-LLM) developed by amadeusai. It is built upon the robust Qwen2.5-7B base model, undergoing a targeted fine-tuning process for two epochs using a substantial 600,000 instruction dataset.

Key Capabilities & Features

  • Brazilian Portuguese Optimization: Specifically fine-tuned to understand and generate high-quality text in Brazilian Portuguese, making it highly suitable for regional applications.
  • Qwen2.5 Architecture: Utilizes a Transformer-based architecture incorporating advanced features like RoPE, SwiGLU, RMSNorm, and Attention QKV bias, pre-trained via Causal Language Modeling.
  • Significant Context Length: Boasts an impressive context length of 131,072 tokens, allowing it to process and generate longer, more coherent texts while maintaining context.
  • Instruction-Following: Enhanced through instruction-tuning, enabling it to follow complex commands and generate relevant responses.
  • Model Size: A 7.62 billion parameter model, offering a balance between performance and computational efficiency.

When to Use This Model

This model is particularly well-suited for applications requiring strong language understanding and generation capabilities in Brazilian Portuguese. It excels in scenarios where instruction-following is critical, such as:

  • Chatbots and Virtual Assistants: Developing conversational AI agents for the Brazilian market.
  • Content Generation: Creating articles, summaries, or creative text in Brazilian Portuguese.
  • Language Translation & Localization: Assisting with tasks that require nuanced understanding of Brazilian Portuguese.
  • Instruction-based tasks: Any application where the model needs to respond accurately to specific user instructions in Portuguese.

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

Finetunes
1 models