Model Overview

SKOTK/dpo-qwen-cot-merged is a 4 billion parameter language model derived from Qwen/Qwen3-4B-Instruct-2507. It has undergone fine-tuning using Direct Preference Optimization (DPO) via the Unsloth library, resulting in a full-merged 16-bit model that requires no adapter loading.

Key Capabilities

• Enhanced Reasoning: Optimized to improve Chain-of-Thought (CoT) reasoning, making it suitable for complex problem-solving tasks.
• Structured Response Quality: Fine-tuned to produce higher quality and more aligned structured outputs based on preferred examples.
• DPO Alignment: Benefits from DPO training, aligning its responses more closely with desired human preferences.

Training Details

The model was trained for 1 epoch with a learning rate of 1e-07 and a beta value of 0.1, using a maximum sequence length of 1024. The training utilized a specific preference dataset (u-10bei/dpo-dataset-qwen-cot) to guide the DPO process. The base model's license terms (MIT License) apply.

Good For

• Applications requiring improved reasoning and logical coherence in responses.
• Generating structured outputs that adhere to specific formats or preferences.
• Tasks where alignment with human preferences is crucial for output quality.