slices: | |
- sources: | |
- model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v | |
layer_range: [0, 15] | |
- model: bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V | |
layer_range: [0, 15] | |
parameters: | |
t: | |
- value: 0.8 | |
- sources: | |
- model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v | |
layer_range: [15, 30] | |
- model: bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V | |
layer_range: [15, 30] | |
parameters: | |
t: | |
- value: [0.8, 1.0, 0.8] | |
- sources: | |
- model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v | |
layer_range: [30, 40] | |
- model: bamec66557/MISCHIEVOUS-12B-Mix_III_ex_V | |
layer_range: [30, 40] | |
parameters: | |
t: | |
- value: 1.0 | |
- filter: self_attn | |
value: [0.9, 1.0, 1.1] | |
merge_method: slerp | |
base_model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v | |
dtype: bfloat16 | |
regularization: | |
- method: weight_clipping | |
clip_range: [-0.1, 0.1] | |
postprocessing: | |
- operation: gaussian_smoothing | |
sigma: 1.2 | |
- operation: normalize |