Model Overview

This model, nakamuratoshiya/dpo-qwen-cot-merged, is a 4 billion parameter language model based on the Qwen/Qwen3-4B-Instruct-2507 architecture. It has been fine-tuned by nakamuratoshiya using Direct Preference Optimization (DPO) via the Unsloth library, resulting in a full-merged 16-bit weight model that requires no adapter loading.

Key Capabilities

• Enhanced Reasoning: Optimized specifically to improve Chain-of-Thought (CoT) reasoning, making it suitable for complex problem-solving tasks.
• Structured Response Quality: DPO training focused on aligning responses with preferred outputs, leading to higher quality and more structured generations.
• Efficient Deployment: Provided as a fully merged model, simplifying deployment with the transformers library.

Training Details

The model underwent 2 epochs of DPO training with a learning rate of 1e-07 and a beta value of 0.3. It utilized a maximum sequence length of 1024. The training data was sourced from the u-10bei/dpo-dataset-qwen-cot dataset. Users should adhere to the MIT License of the dataset and the original base model's license terms.