Model Overview

Hi-Satoh/adv_sft_dpo_final_3_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 16-bit weights fully merged into the base model.

Key Capabilities

• Enhanced Reasoning: Optimized to improve Chain-of-Thought reasoning, enabling more structured and logical outputs.
• Improved Response Quality: DPO training aligns the model's responses with preferred outputs, leading to higher quality and more coherent generations.
• Structured Output Generation: Focuses on generating structured responses based on preference datasets.

Training Details

The model underwent 1 epoch of DPO training with a learning rate of 7e-06 and a beta value of 0.5. It utilized a maximum sequence length of 4096 tokens. The training data used was [Hi-Satoh/test_dpo_dataset].

Good For

• Applications requiring models with strong reasoning abilities.
• Scenarios where structured and aligned outputs are critical.
• Tasks benefiting from preference-tuned response generation.