| models: | |
| - model: VAGOsolutions/SauerkrautLM-v2-14b-DPO | |
| parameters: | |
| weight: 0.20 # Strong IFEval and factual reasoning baseline | |
| density: 0.6 | |
| - model: allknowingroger/QwenSlerp6-14B | |
| parameters: | |
| weight: 0.20 # Balanced reasoning across multiple benchmarks | |
| density: 0.6 | |
| - model: CultriX/SeQwence-14B-EvolMerge | |
| parameters: | |
| weight: 0.15 # Generalist model for BBH and MUSR | |
| density: 0.5 | |
| - model: CultriX/Qwen2.5-14B-Wernicke | |
| parameters: | |
| weight: 0.15 # QA leader for GPQA and MUSR | |
| density: 0.6 # Increase density to preserve more QA-specific parameters | |
| - model: qingy2019/Qwen2.5-Math-14B-Instruct | |
| parameters: | |
| weight: 0.15 # Specialist for MATH and advanced reasoning | |
| density: 0.6 | |
| - model: sometimesanotion/Qwen2.5-14B-Vimarckoso | |
| parameters: | |
| weight: 0.10 # MUSR leader for nuanced multi-step reasoning | |
| density: 0.5 | |
| - model: CultriX/Qwen2.5-14B-SLERPv7 | |
| parameters: | |
| weight: 0.05 # Contextual reasoning support for BBH and tiny benchmarks | |
| density: 0.5 | |
| base_model: CultriX/SeQwence-14Bv1 | |
| merge_method: dare_ties | |
| parameters: | |
| normalize: true | |
| int8_mask: true | |
| dtype: bfloat16 | |
| adaptive_merge_parameters: | |
| task_weights: | |
| IFEval: 1.3 # Enhanced instruction-following and factual tasks | |
| BBH: 1.3 # Strengthened complex reasoning capabilities | |
| MATH_Lvl_5: 1.4 # Prioritize advanced mathematical tasks | |
| GPQA: 1.4 # Boost graduate-level knowledge capabilities | |
| MuSR: 1.3 # Strengthen multi-step reasoning on complex tasks | |
| MMLU_PRO: 1.2 # Ensure broad domain understanding | |
| smoothing_factor: 0.15 # Sharper blending for reasoning and factual tasks | |
| gradient_clipping: 0.9 # Tighter control for precise parameter scaling | |