merge_method: dare_ties dtype: bfloat16 normalize: true base_model: Qwen/Qwen2.5-3B-Instruct models: - model: PowerInfer/SmallThinker-3B-Preview parameters: weight: .6 density: .45 - model: prithivMLmods/QwQ-LCoT-3B-Instruct parameters: weight: .4 density: .85