TurkishReasoner-Qwen2.5-3B is a mid-sized Turkish reasoning model built on Qwen's efficient Qwen2.5-3B foundation. This model provides an excellent balance between performance and computational efficiency, delivering structured reasoning capabilities in Turkish while requiring moderate resources for deployment.

Key Features

Built on Qwen's efficient 3B parameter architecture
Specialized for Turkish reasoning with structured output format
Excellent balance between performance and resource requirements
Strong support for structured data and structured outputs
Enhanced instruction following for reasoning tasks
Support for multilingual context with Turkish optimization

Technical Specifications

Base Model: Qwen/Qwen2.5-3B
Parameters: 3.09 billion
Input: Text
Hardware Requirements: ~8GB VRAM
Training Infrastructure: NVIDIA T4 GPU

Usage

This model is ideal for applications requiring solid reasoning in Turkish with moderate computational resources:

Educational applications requiring detailed problem-solving
Mid-tier deployment environments with limited GPU resources
Applications balancing reasoning quality with efficiency requirements
Development and prototyping of reasoning-intensive applications

Example Usage

python

from transformers import pipeline

pipe = pipeline("text-generation", model="Chan-Y/TurkishReasoner-Qwen2.5-3B", device=0)

messages = [
    {"role": "system", "content": """Sen kullanıcıların isteklerine Türkçe cevap veren bir asistansın ve sana bir problem verildi.
Problem hakkında düşün ve çalışmanı göster.
Çalışmanı <start_working_out> ve <end_working_out> arasına yerleştir.
Sonra, çözümünü <SOLUTION> ve </SOLUTION> arasına yerleştir.
Lütfen SADECE Türkçe kullan."""},
    {"role": "user", "content": "121'in karekökü kaçtır?"},
]

response = pipe(messages)
print(response)

For more information or assistance with this model, please contact the developers:

Cihan Yalçın: https://www.linkedin.com/in/chanyalcin/
Şevval Nur Savcı: https://www.linkedin.com/in/%C5%9Fevval-nur-savc%C4%B1/