TakaYamamoto/dpo-qwen-cot-merged_biya
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Feb 6, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

TakaYamamoto/dpo-qwen-cot-merged_biya is a 4 billion parameter language model fine-tuned from Qwen3-4B-Instruct-2507 using Direct Preference Optimization (DPO). This model is specifically optimized to improve reasoning capabilities through Chain-of-Thought (CoT) and enhance structured response quality. It features a 40960 token context length and is designed for tasks requiring aligned, high-quality outputs.

Loading preview...