AshleyQu0311/dpo-qwen-cot-merged
AshleyQu0311/dpo-qwen-cot-merged is a 4 billion parameter Qwen3-based causal language model, fine-tuned using Direct Preference Optimization (DPO) via Unsloth. This model is specifically optimized to improve reasoning capabilities, particularly Chain-of-Thought (CoT), and enhance the quality of structured responses. With a context length of 40960 tokens, it is designed for applications requiring precise, aligned, and well-reasoned outputs.
Loading preview...
Overview
AshleyQu0311/dpo-qwen-cot-merged is a 4 billion parameter language model built upon the Qwen3-4B-Instruct-2507 base model. It has been fine-tuned using Direct Preference Optimization (DPO) with the Unsloth library, resulting in a full-merged 16-bit weight model that requires no adapter loading.
Key Capabilities
- Enhanced Reasoning: Optimized to improve Chain-of-Thought (CoT) reasoning, making it suitable for tasks requiring multi-step logical deduction.
- Structured Response Quality: Aligned to produce preferred outputs and higher quality structured responses based on its DPO training.
- Efficient Deployment: Provided as a fully merged model, simplifying integration and usage with the
transformerslibrary.
Training Details
The model underwent 1 epoch of DPO training with a learning rate of 5e-07 and a beta value of 0.1. It utilized a maximum sequence length of 1024 during training 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.
Licensing
This model is released under the MIT License, consistent with its training dataset. Users must also adhere to the license terms of the original Qwen3 base model.