| merge_method: della_linear | |
| base_model: CultriX/Qwen2.5-14B-Wernickev3 | |
| dtype: bfloat16 | |
| parameters: | |
| epsilon: 0.01 # Reduced from 0.012 for even finer parameter scaling, enhancing precision in blending. | |
| lambda: 1.5 # Increased from 1.4 to further emphasize significant model contributions, particularly from specialized models. | |
| normalize: true # Maintains balanced parameter integration, crucial for stability across diverse benchmarks. | |
| adaptive_merge_parameters: | |
| task_weights: | |
| tinyArc: 1.65 # Increased from 1.6 to further boost logical reasoning, leveraging Qwen2.5-14B-Broca's strength. | |
| tinyHellaswag: 1.55 # Slightly increased from 1.5 to enhance contextual understanding, supported by SeQwence-14Bv1. | |
| tinyMMLU: 1.7 # Increased from 1.65 for improved domain knowledge, utilizing Qwenfinity-2.5-14B's broad capabilities. | |
| tinyTruthfulQA: 1.95 # Slightly increased from 1.9 to maximize accurate factual reasoning, with Qwenfinity-2.5-14B's contribution. | |
| tinyTruthfulQA_mc1: 1.75 # Increased from 1.7 for enhanced multiple-choice reasoning, supported by Qwen2.5-14B-Emergedv3. | |
| tinyWinogrande: 1.8 # Increased from 1.75 for advanced reasoning and contextual prediction, leveraging Qwen2.5-14B-Broca. | |
| IFEval: 2.0 # Increased from 1.9 to prioritize instruction-following, with Q2.5-Veltha-14B-0.5's strong performance. | |
| BBH: 1.75 # Slightly increased from 1.7 for complex reasoning, supported by SeQwence-14B-EvolMerge's strength. | |
| MATH: 2.2 # Increased from 2.1 to maximize mathematical reasoning, with Qwen2.5-Math-14B-Instruct's specialization. | |
| GPQA: 1.85 # Increased from 1.8 for enhanced graduate-level QA, leveraging Qwen2.5-14B-Wernicke's capabilities. | |
| MUSR: 1.95 # Increased from 1.9 for strengthened multi-step reasoning, with Qwen2.5-14B-Vimarckoso's expertise. | |
| MMLU-PRO: 1.85 # Increased from 1.8 to further boost domain multitask performance, utilizing QwenSlerp6-14B. | |
| smoothing_factor: 0.08 # Reduced from 0.1 for more precise blending, allowing distinct model strengths to be preserved. | |
| gradient_clipping: | |
| CultriX/Qwen2.5-14B-Wernickev3: 0.85 # Slightly reduced from 0.86 to allow a bit more contribution from the base model. | |
| CultriX/Qwenfinity-2.5-14B: 0.82 # Reduced from 0.83 to balance its broad multitask contribution. | |
| djuna/Q2.5-Veltha-14B-0.5: 0.92 # Slightly increased from 0.91 to allow more contribution in advanced reasoning. | |
| CultriX/Qwen2.5-14B-Broca: 0.86 # Slightly increased from 0.85 to leverage its logical reasoning strengths. | |
| qingy2019/Qwen2.5-Math-14B-Instruct: 0.94 # Increased from 0.93 to maximize its mathematical reasoning contribution. | |
| CultriX/SeQwence-14Bv1: 0.87 # Slightly reduced from 0.88 to balance its generalist multitask support. | |
| sometimesanotion/Qwen2.5-14B-Vimarckoso: 0.90 # Increased from 0.89 for enhanced multi-step reasoning. | |
| allknowingroger/QwenSlerp6-14B: 0.86 # Slightly reduced from 0.87 to refine its contextual reasoning integration. | |
| models: | |
| - model: CultriX/Qwen2.5-14B-Wernickev3 | |
| parameters: | |
| weight: 0.25 # Slightly reduced from 0.26 to balance with other models while maintaining a strong foundation. | |
| density: 0.72 # Increased from 0.7 to preserve more of its critical reasoning parameters. | |
| - model: CultriX/Qwenfinity-2.5-14B | |
| parameters: | |
| weight: 0.22 # Slightly reduced from 0.23 for a more balanced contribution across its broad capabilities. | |
| density: 0.68 # Increased from 0.65 to retain more of its multitask performance. | |
| - model: djuna/Q2.5-Veltha-14B-0.5 | |
| parameters: | |
| weight: 0.20 # Reduced from 0.22 to balance its specialized contributions with the overall blend. | |
| density: 0.75 # Increased from 0.72 to further leverage its strengths in IFEval and advanced reasoning. | |
| - model: CultriX/Qwen2.5-14B-Broca | |
| parameters: | |
| weight: 0.16 # Slightly increased from 0.15 to enhance its logical reasoning and factual QA contributions. | |
| density: 0.68 # Increased from 0.65 to preserve more of its capabilities in the tiny benchmarks. | |
| - model: qingy2019/Qwen2.5-Math-14B-Instruct | |
| parameters: | |
| weight: 0.19 # Slightly increased from 0.18 to further emphasize mathematical reasoning. | |
| density: 0.75 # Increased from 0.73 to retain more of its specialized mathematical parameters. | |
| - model: CultriX/SeQwence-14Bv1 | |
| parameters: | |
| weight: 0.13 # Slightly reduced from 0.14 to fine-tune its generalist multitask support. | |
| density: 0.65 # Increased from 0.63 to preserve more of its diverse capabilities. | |
| - model: sometimesanotion/Qwen2.5-14B-Vimarckoso | |
| parameters: | |
| weight: 0.11 # Slightly reduced from 0.12 to balance its multi-step reasoning contributions. | |
| density: 0.62 # Increased from 0.6 to retain more of its specialized reasoning strengths. | |
| - model: allknowingroger/QwenSlerp6-14B | |
| parameters: | |
| weight: 0.09 # Slightly reduced from 0.1 to refine its contextual reasoning contributions. | |
| density: 0.65 # Increased from 0.62 to preserve more of its capabilities in MMLU-PRO and contextual tasks. |