models: | |
- model: CultriX/Qwen2.5-14B-Wernicke | |
parameters: | |
weight: 0.25 # GPQA leader, also strong in MUSR/MMLU-PRO | |
density: 0.6 # Retain majority for complex reasoning tasks | |
- model: VAGOsolutions/SauerkrautLM-v2-14b-DPO | |
parameters: | |
weight: 0.25 # Top IFEval and good MATH support | |
density: 0.6 # Ensure factual and mathematical integrity | |
- model: allknowingroger/QwenStock3-14B | |
parameters: | |
weight: 0.20 # Highest MMLU-PRO for broad domain strength | |
density: 0.5 # Balanced retention for general expertise | |
- model: CultriX/SeQwence-14B | |
parameters: | |
weight: 0.20 # Near-top MATH and well-rounded performance | |
density: 0.5 # Efficient parameter usage for stable improvement | |
- model: sometimesanotion/Lamarck-14B-v0.3 | |
parameters: | |
weight: 0.05 # Top BBH to ensure benchmark coverage | |
density: 0.4 # Light integration focusing on key parameters | |
- model: sometimesanotion/Qwen2.5-14B-Vimarckoso | |
parameters: | |
weight: 0.05 # MUSR leader for nuanced, multi-step reasoning | |
density: 0.4 # Targeted retention for domain-specific strengths | |
base_model: Qwen/Qwen2.5-14B | |
merge_method: dare_ties | |
parameters: | |
normalize: true # Ensure parameter scale alignment | |
int8_mask: true # Memory/computation efficiency | |
dtype: bfloat16 | |
tokenizer_source: Qwen/Qwen2.5-14B-Instruct | |