| merge_method: dare_ties | |
| base_model: CultriX/Qwen2.5-14B-Wernickev3 | |
| dtype: bfloat16 | |
| parameters: | |
| epsilon: 0.0075 | |
| lambda: 2.1 | |
| normalize: true | |
| adaptive_merge_parameters: | |
| task_weights: | |
| tinyArc: 2.1 | |
| tinyHellaswag: 1.9 | |
| tinyMMLU: 2.1 | |
| tinyTruthfulQA: 2.5 | |
| tinyTruthfulQA_mc1: 2.4 | |
| tinyWinogrande: 2.4 | |
| IFEval: 2.4 | |
| BBH: 2.3 | |
| MATH: 2.6 | |
| GPQA: 2.4 | |
| MUSR: 2.5 | |
| MMLU-PRO: 2.2 | |
| smoothing_factor: 0.05 | |
| gradient_clipping: | |
| CultriX/Qwen2.5-14B-Wernickev3: 0.82 | |
| djuna/Q2.5-Veltha-14B-0.5: 0.84 | |
| qingy2019/Qwen2.5-Math-14B-Instruct: 0.87 | |
| CultriX/SeQwence-14Bv1: 0.8 | |
| CultriX/Qwen2.5-14B-Broca: 0.85 | |
| CultriX/Qwen2.5-14B-Brocav3: 0.83 | |
| CultriX/Qwen2.5-14B-Brocav7: 0.84 | |
| allknowingroger/QwenSlerp6-14B: 0.8 | |
| models: | |
| - model: CultriX/Qwen2.5-14B-Wernickev3 | |
| parameters: | |
| weight: 0.21 | |
| density: 0.78 | |
| - model: djuna/Q2.5-Veltha-14B-0.5 | |
| parameters: | |
| weight: 0.2 | |
| density: 0.76 | |
| - model: qingy2019/Qwen2.5-Math-14B-Instruct | |
| parameters: | |
| weight: 0.18 | |
| density: 0.75 | |
| - model: CultriX/SeQwence-14Bv1 | |
| parameters: | |
| weight: 0.17 | |
| density: 0.74 | |
| - model: CultriX/Qwen2.5-14B-Broca | |
| parameters: | |
| weight: 0.17 | |
| density: 0.74 | |
| - model: CultriX/Qwen2.5-14B-Brocav3 | |
| parameters: | |
| weight: 0.15 | |
| density: 0.73 | |
| - model: CultriX/Qwen2.5-14B-Brocav7 | |
| parameters: | |
| weight: 0.14 | |
| density: 0.72 | |
| - model: allknowingroger/QwenSlerp6-14B | |
| parameters: | |
| weight: 0.13 | |
| density: 0.72 | |
| tokenizer_source: CultriX/Qwen2.5-14B-Wernickev3 | |