| models: | |
| - model: CultriX/SeQwence-14Bv1 | |
| parameters: | |
| weight: 0.22 # Boosted slightly to improve general task performance | |
| density: 0.62 # Prioritize generalist adaptability | |
| - model: allknowingroger/QwenSlerp6-14B | |
| parameters: | |
| weight: 0.18 | |
| density: 0.59 # Slight increase to enhance contextual reasoning (tinyHellaswag) | |
| - model: CultriX/Qwen2.5-14B-Wernickev3 | |
| parameters: | |
| weight: 0.16 | |
| density: 0.56 # Minor increase to stabilize GPQA and MUSR performance | |
| - model: CultriX/Qwen2.5-14B-Emergedv3 | |
| parameters: | |
| weight: 0.15 # Increase weight for domain-specific expertise | |
| density: 0.55 | |
| - model: VAGOsolutions/SauerkrautLM-v2-14b-DPO | |
| parameters: | |
| weight: 0.12 | |
| density: 0.56 # Enhance factual reasoning and IFEval contributions | |
| - model: CultriX/Qwen2.5-14B-Unity | |
| parameters: | |
| weight: 0.10 | |
| density: 0.53 | |
| - model: qingy2019/Qwen2.5-Math-14B-Instruct | |
| parameters: | |
| weight: 0.10 | |
| density: 0.51 # Retain focus on MATH and advanced reasoning tasks | |
| merge_method: dare_ties | |
| base_model: CultriX/SeQwence-14Bv1 | |
| parameters: | |
| normalize: true | |
| int8_mask: true | |
| dtype: bfloat16 | |
| tokenizer_source: Qwen/Qwen2.5-14B-Instruct | |
| adaptive_merge_parameters: | |
| task_weights: | |
| IFEval: 1.5 # Strengthened for better instruction-following | |
| BBH: 1.3 | |
| MATH: 1.6 # Emphasize advanced reasoning and problem-solving | |
| GPQA: 1.4 # Improve factual recall and logical QA tasks | |
| MUSR: 1.5 # Strengthened multi-step reasoning capabilities | |
| MMLU-PRO: 1.3 # Slight boost for domain-specific multitask knowledge | |
| smoothing_factor: 0.19 # Refined for smoother blending of task strengths | |
| gradient_clipping: 0.88 # Tightened slightly for precise parameter contribution | |