| ### CONFIG SuperiorMerge-14B-From-2-to-10 ### | |
| models: | |
| - model: VAGOsolutions/SauerkrautLM-v2-14b-DPO | |
| parameters: | |
| weight: 0.25 # Prioritize top IFEval | |
| density: 0.6 # Keep a large portion for strong factual baseline | |
| - model: allknowingroger/QwenSlerp6-14B | |
| parameters: | |
| weight: 0.25 # High weight for MATH and balanced reasoning | |
| density: 0.6 # Retain robust reasoning capabilities | |
| - model: CultriX/SeQwence-14B-EvolMerge | |
| parameters: | |
| weight: 0.20 # Important for best BBH and near-top MUSR | |
| density: 0.5 # Moderate density to ensure these strengths blend well | |
| - model: CultriX/Qwen2.5-14B-Wernicke | |
| parameters: | |
| weight: 0.15 # Adds top GPQA performance | |
| density: 0.5 # Sufficient to preserve QA strengths | |
| - model: allknowingroger/QwenStock3-14B | |
| parameters: | |
| weight: 0.15 # For top MMLU-PRO, enhancing domain knowledge | |
| density: 0.5 # Balanced integration of diverse subject expertise | |
| base_model: Qwen/Qwen2.5-14B | |
| merge_method: dare_ties | |
| parameters: | |
| normalize: true # Ensures parameter scaling compatibility | |
| int8_mask: true # Memory and computational efficiency | |
| dtype: bfloat16 | |
| tokenizer_source: Qwen/Qwen2.5-14B-Instruct | |
| ### END OF CONFIG SuperiorMerge-14B-From-2-to-10 ### | |