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

demimomi/dpo-qwen-cot-merged is a 4 billion parameter Qwen3-Instruct causal language model, fine-tuned by demimomi using Direct Preference Optimization (DPO) with the Unsloth library. This model is specifically optimized to improve reasoning capabilities through Chain-of-Thought (CoT) and enhance structured response quality. It is designed for applications requiring aligned and coherent text generation.

Loading preview...