| merge_method: della_linear | |
| base_model: CultriX/Qwen2.5-14B-Wernickev3 | |
| dtype: bfloat16 | |
| parameters: | |
| epsilon: 0.03 # Refines sharper parameter scaling. | |
| lambda: 1.1 # Balances blending while emphasizing significant contributions. | |
| normalize: true # Ensures stable parameter integration across models. | |
| adaptive_merge_parameters: | |
| task_weights: | |
| tinyArc: 1.5 # Logical reasoning boost. | |
| tinyHellaswag: 1.3 # Contextual and multi-step reasoning. | |
| tinyMMLU: 1.2 # Domain-specific knowledge retention. | |
| tinyTruthfulQA: 1.6 # Enhanced factual QA tasks. | |
| tinyTruthfulQA_mc1: 1.4 | |
| tinyWinogrande: 1.5 # Reasoning for multi-turn tasks. | |
| IFEval: 1.6 # Instruction-following. | |
| BBH: 1.5 # Complex reasoning improvement. | |
| MATH: 1.7 # Mathematical reasoning focus. | |
| GPQA: 1.6 # Graduate-level QA emphasis. | |
| MUSR: 1.6 # Advanced multi-step reasoning. | |
| MMLU-PRO: 1.5 # Multitask domain performance. | |
| smoothing_factor: 0.15 # Balance model contributions. | |
| gradient_clipping: 0.85 # Ensures no single model overly dominates. | |
| models: | |
| - model: CultriX/Qwen2.5-14B-Wernickev3 | |
| parameters: | |
| weight: 0.2 # Core multitask foundation. | |
| density: 0.7 | |
| - model: CultriX/Qwenfinity-2.5-14B | |
| parameters: | |
| weight: 0.18 # Broad multitask capabilities. | |
| density: 0.65 | |
| - model: CultriX/Qwen2.5-14B-Broca | |
| parameters: | |
| weight: 0.15 # Logical reasoning and multitask adaptability. | |
| density: 0.6 | |
| - model: djuna/Q2.5-Veltha-14B-0.5 | |
| parameters: | |
| weight: 0.15 # Specialized for MUSR, IFEval, and BBH. | |
| density: 0.6 | |
| - model: qingy2019/Qwen2.5-Math-14B-Instruct | |
| parameters: | |
| weight: 0.12 # Mathematical reasoning contributor. | |
| density: 0.6 | |
| - model: CultriX/SeQwence-14Bv1 | |
| parameters: | |
| weight: 0.12 # Broad multitask contributor. | |
| density: 0.6 | |
| - model: sometimesanotion/Qwen2.5-14B-Vimarckoso | |
| parameters: | |
| weight: 0.08 # Specialist for MUSR and advanced reasoning tasks. | |
| density: 0.5 | |
| tokenizer_source: CultriX/Qwen2.5-14B-Wernickev3 | |