cnmoro/Qwen2.5-0.5B-Portuguese-Hybrid-Reasoning

Hugging Face
TEXT GENERATIONConcurrent Unit Cost:1Model Size:0.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Mar 3, 2025License:mitArchitecture:Transformer0.0K Open Weights Featherless Exclusive Warm

cnmoro/Qwen2.5-0.5B-Portuguese-Hybrid-Reasoning is a 0.5 billion parameter Qwen2.5 model fine-tuned for enhanced proficiency in the Portuguese language. It features a unique hybrid reasoning capability that can be toggled on or off, allowing for explicit thought processes. With a 32768-token context length, this model is optimized for Portuguese-centric natural language processing tasks and applications requiring adaptable reasoning.

Loading preview...

cnmoro/Qwen2.5-0.5B-Portuguese-Hybrid-Reasoning Overview

This model is a 0.5 billion parameter variant of the Qwen2.5 architecture, specifically fine-tuned by cnmoro to achieve high proficiency in the Portuguese language. A key differentiator is its "Hybrid Reasoning" feature, which allows users to explicitly enable or disable an internal thought process for generating responses. When reasoning is enabled, the model can output its step-by-step thinking before providing a final answer, which can be beneficial for complex problem-solving and transparency.

Key Capabilities

  • Portuguese Language Proficiency: Optimized for understanding and generating high-quality text in Portuguese.
  • Toggleable Reasoning: Users can activate an explicit reasoning mode by using a "Reason" system message, allowing the model to show its thought process.
  • Qwen2.5 Architecture: Leverages the robust Qwen2.5 base for strong foundational language understanding.
  • Extended Context Window: Supports a context length of 32768 tokens, enabling processing of longer texts.

Performance in Portuguese

Evaluated on the Open Portuguese LLM Leaderboard, the model achieved an Average score of 46.91. Notable scores include 82.67 on Assin2 RTE and 63.32 on FaQuAD NLI, indicating strong performance in specific Portuguese NLP tasks.

Good for

  • Applications requiring advanced Portuguese language generation and comprehension.
  • Use cases where explicit reasoning or step-by-step problem-solving is beneficial.
  • Developing chatbots, content generation tools, or analytical systems tailored for Portuguese speakers.