tarona/qwen3-4b-dpo-marged_001
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Feb 5, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The tarona/qwen3-4b-dpo-marged_001 model 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 and improve the quality of structured responses. It is designed for tasks requiring aligned and preferred outputs based on its DPO training on a specialized preference dataset.

Loading preview...

Model Overview

tarona/qwen3-4b-dpo-marged_001 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, resulting in a full-merged 16-bit weight model that requires no adapter loading.

Key Capabilities

  • Enhanced Reasoning: Optimized to improve Chain-of-Thought reasoning processes.
  • Structured Response Quality: Focuses on generating higher quality and more structured outputs.
  • Preference Alignment: Fine-tuned with DPO to align responses with preferred outputs based on a specific preference dataset (u-10bei/dpo-dataset-qwen-cot).

Training Details

The model was trained 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 the DPO process. The LoRA configuration (r=8, alpha=16) was merged directly into the base model.

Recommended Use Cases

  • Applications requiring improved reasoning abilities.
  • Scenarios where structured and high-quality responses are critical.
  • Tasks benefiting from a model aligned with specific preferred output styles.