gakhg/dpo-qwen-cot-merged
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Feb 5, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The gakhg/dpo-qwen-cot-merged model is a 4 billion parameter language model, fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using Direct Preference Optimization (DPO). It is specifically optimized to enhance reasoning capabilities (Chain-of-Thought) and improve the quality of structured responses. This model is designed for applications requiring robust logical inference and well-formed outputs, leveraging its 40960-token context length.

Loading preview...

Model Overview

This model, gakhg/dpo-qwen-cot-merged, is a 4 billion parameter language model derived from Qwen/Qwen3-4B-Instruct-2507. It has undergone Direct Preference Optimization (DPO) using the Unsloth library to align its responses with preferred outputs.

Key Capabilities

  • Enhanced Reasoning: Optimized to improve Chain-of-Thought (CoT) reasoning, making it suitable for tasks requiring logical steps and inference.
  • Structured Response Quality: Focuses on generating higher quality, more structured outputs based on preference datasets.
  • Full-Merged Weights: Provided as full-merged 16-bit weights, eliminating the need for adapter loading and simplifying deployment with transformers.

Training Details

The model was fine-tuned for 1 epoch with a learning rate of 1e-07 and a beta value of 0.1. It utilized a maximum sequence length of 1024 during training. The LoRA configuration (r=8, alpha=16) was merged into the base model.

Good For

  • Applications requiring improved logical reasoning and problem-solving.
  • Generating structured and coherent text responses.
  • Use cases where direct preference alignment is beneficial for output quality.

Licensing

This model uses the u-10bei/dpo-dataset-qwen-cot for training, which is under the MIT License. Users must also comply with the original base model's license terms.