rmbrain/dpo-qwen-cot-merged
rmbrain/dpo-qwen-cot-merged is a 4 billion parameter language model, fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using Direct Preference Optimization (DPO). This model is specifically optimized to enhance reasoning capabilities through Chain-of-Thought (CoT) and improve the quality of structured responses. It is designed for tasks requiring logical deduction and well-organized output, leveraging its DPO training on a preference dataset.
Loading preview...
Model Overview
rmbrain/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 LoRA adapters merged into the base model for direct use.
Key Capabilities
- Enhanced Reasoning: Optimized to improve Chain-of-Thought (CoT) reasoning, enabling more logical and step-by-step problem-solving.
- Structured Response Quality: DPO training specifically targeted at aligning responses with preferred outputs, leading to higher quality and more structured generated text.
- Efficient Deployment: Provided as a full-merged 16-bit model, eliminating the need for adapter loading and simplifying integration with the
transformerslibrary.
Training Details
The model underwent 1 epoch of DPO training with a learning rate of 1e-07 and a beta value of 0.1. It utilized a maximum sequence length of 1024. The training data was sourced from the u-10bei/dpo-dataset-qwen-cot dataset. The model operates under an MIT License, with users also required to comply with the original base model's license terms.