| slices: | |
| - sources: | |
| - model: bamec66557/mergekit-slerp-xjlmywj | |
| layer_range: [0, 20] | |
| - model: bamec66557/MISCHIEVOUS-12B-Mix_0.3v | |
| layer_range: [0, 20] | |
| parameters: | |
| t: | |
| - value: 0.8 | |
| - sources: | |
| - model: bamec66557/mergekit-slerp-xjlmywj | |
| layer_range: [20, 40] | |
| - model: bamec66557/MISCHIEVOUS-12B-Mix_0.3v | |
| layer_range: [20, 40] | |
| parameters: | |
| t: | |
| - value: 1.0 | |
| - filter: self_attn | |
| value: [0.8, 0.9, 1.0, 1.1, 1.2] | |
| merge_method: slerp # Preserve merge method | |
| base_model: bamec66557/mergekit-slerp-xjlmywj # Base model | |
| dtype: bfloat16 # Data types for fast merges | |
| # Additional options | |
| regularization: | |
| - method: weight_clipping | |
| clip_range: [-0.1, 0.1] | |
| postprocessing: | |
| - operation: gaussian_smoothing | |
| sigma: 1.5 # Gaussian smoothing intensity | |
| - operation: smoothing | |
| parameters: | |
| adaptive: true | |
| range: [0.8, 1.2] # Adaptively adjust | |
| kernel_size: 5 # Smoothing larger ranges with increased kernel size | |
| - operation: normalize # Normalise after merge | |