Model Overview

yukiakari/dpo-qwen-cot-merged is a 4 billion parameter language model derived from Qwen/Qwen3-4B-Instruct-2507. It has been fine-tuned using Direct Preference Optimization (DPO) via the Unsloth library, with its 16-bit weights fully merged for direct use without adapter loading.

Key Capabilities

• Enhanced Reasoning: Optimized to improve Chain-of-Thought (CoT) reasoning, making it suitable for complex problem-solving tasks.
• Structured Responses: Focuses on generating higher quality, more structured outputs based on preference datasets.
• Efficient Deployment: Provided as a full-merged model, simplifying integration into existing transformers workflows.

Training Details

The model underwent 1 epoch of DPO training with a learning rate of 1e-05 and a beta value of 0.1. It utilized a maximum sequence length of 1024 and incorporated LoRA configuration (r=8, alpha=16) which was subsequently merged into the base model. The training data used was u-10bei/dpo-dataset-qwen-cot.

Usage Considerations

This model is licensed under the MIT License, aligning with its training dataset. Users must also adhere to the original base model's license terms.