| merge_method: della_linear | |
| base_model: CultriX/Qwen2.5-14B-Wernickev3 | |
| dtype: bfloat16 | |
| out_dtype: bfloat16 | |
| parameters: | |
| epsilon: 0.009 # Further reduced for ultra-fine parameter scaling. | |
| lambda: 1.6 # Increased to emphasize significant model contributions. | |
| normalize: true # Balances the parameter integration for stability. | |
| rescale: true # Enabled to align parameter scales across models. | |
| int8_mask: false # Disabled to allow full-precision computations for enhanced accuracy. | |
| density: 0.90 # Balanced density for optimal generalization and performance. | |
| adaptive_merge_parameters: | |
| task_weights: | |
| tinyArc: 1.6 # Prioritizes logical reasoning improvements. | |
| tinyHellaswag: 1.5 # Strengthened contextual understanding and consistency. | |
| tinyMMLU: 1.8 # Enhanced domain knowledge for multitask benchmarks. | |
| tinyTruthfulQA: 1.9 # Maximized for accurate factual reasoning and QA. | |
| tinyTruthfulQA_mc1: 1.75 # Increased focus for multiple-choice reasoning. | |
| tinyWinogrande: 1.75 # Advanced reasoning and contextual prediction improvement. | |
| IFEval: 2.15 # Enhanced instruction-following tasks boosted by multitask contributors. | |
| BBH: 1.95 # Further improved for complex reasoning tasks. | |
| MATH: 2.45 # Highest priority, focusing on mathematical excellence. | |
| GPQA: 2.1 # Boosted graduate-level QA capabilities. | |
| MUSR: 1.9 # Nuanced multi-step reasoning strengthened further. | |
| MMLU-PRO: 1.9 # Maximized domain multitask performance. | |
| smoothing_factor: 0.035 # Further reduced for precise task-specific blending. | |
| gradient_clipping: | |
| CultriX/Qwen2.5-14B-Wernickev3: 0.88 # Increased for enhanced stability. | |
| CultriX/Qwenfinity-2.5-14B: 0.85 # Adjusted for consistent multitask integration. | |
| djuna/Q2.5-Veltha-14B-0.5: 0.91 # Maintained advanced reasoning contributions. | |
| CultriX/SeQwence-14B-EvolMerge: 0.88 # Generalist multitask support remains stable. | |
| qingy2024/Fusion4-14B-Instruct: 0.93 # Mathematically focused tasks maximized. | |
| CultriX/Qwen2.5-14B-Emerged: 0.88 # Increased for logical reasoning enhancements. | |
| sometimesanotion/Lamarck-14B-v0.6: 0.89 # Balanced multi-step reasoning contributions. | |
| allknowingroger/QwenSlerp5-14B: 0.87 # Contextual and logical reasoning integration refined. | |
| models: | |
| - model: CultriX/Qwen2.5-14B-Wernickev3 | |
| parameters: | |
| weight: 0.30 # Core backbone for multitask reasoning. | |
| density: 0.75 # Further increased to preserve critical reasoning parameters. | |
| - model: CultriX/Qwenfinity-2.5-14B | |
| parameters: | |
| weight: 0.25 # Comprehensive multitask performer. | |
| density: 0.65 | |
| - model: djuna/Q2.5-Veltha-14B-0.5 | |
| parameters: | |
| weight: 0.25 # Advanced reasoning support for GPQA and MUSR. | |
| density: 0.74 | |
| - model: CultriX/SeQwence-14B-EvolMerge | |
| parameters: | |
| weight: 0.20 # Enhanced contributions to BBH and MUSR. | |
| density: 0.55 | |
| - model: qingy2024/Fusion4-14B-Instruct | |
| parameters: | |
| weight: 0.19 # Mathematical reasoning priority. | |
| density: 0.77 | |
| - model: CultriX/Qwen2.5-14B-Emerged | |
| parameters: | |
| weight: 0.21 # Maintains overall task performance with balanced strengths. | |
| density: 0.72 # Increased for better integration. | |
| - model: CultriX/Qwen2.5-14B-Broca | |
| parameters: | |
| weight: 0.16 # Logical reasoning and factual QA enhancements. | |
| density: 0.68 # Increased to better support Broca's specialized tasks. | |
| - model: sometimesanotion/Lamarck-14B-v0.6 | |
| parameters: | |
| weight: 0.15 # Multi-step reasoning tasks contributor. | |
| density: 0.63 # Slight increase for better integration. | |
| - model: allknowingroger/QwenSlerp5-14B | |
| parameters: | |
| weight: 0.16 # Contextual reasoning improvements. | |
| density: 0.64 # Increased for enhanced performance. | |