sho-nakamura/dpo-qwen-cot-merged
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Feb 28, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The sho-nakamura/dpo-qwen-cot-merged model is a 4 billion parameter Qwen3-based language model fine-tuned using Direct Preference Optimization (DPO) by sho-nakamura. It is specifically optimized for improving reasoning capabilities through Chain-of-Thought (CoT) and generating high-quality structured responses. This model is designed for tasks requiring enhanced logical deduction and formatted output, leveraging its 32K token context length.

Loading preview...