name: tempesthenno-nuslerp-0124 | |
merge_method: nuslerp | |
tokenizer: | |
source: union | |
chat_template: "chatml" | |
dtype: float32 | |
out_dtype: bfloat16 | |
parameters: | |
int8_mask: true | |
normalize: true | |
rescale: false | |
slices: | |
- sources: | |
- model: /Users/sthenno/models/tempesthenno--converge-dtask | |
layer_range: [0, 8] | |
parameters: | |
weight: 0.65 | |
nuslerp_flatten: false | |
nuslerp_row_wise: true | |
- model: /Users/sthenno/models/tempesthenno--converge-breadcrumbs | |
layer_range: [0, 8] | |
parameters: | |
weight: 0.35 | |
nuslerp_flatten: false | |
nuslerp_row_wise: true | |
- sources: | |
- model: /Users/sthenno/models/tempesthenno--converge-dtask | |
layer_range: [8, 16] | |
parameters: | |
weight: 0.60 | |
nuslerp_flatten: false | |
nuslerp_row_wise: true | |
- model: /Users/sthenno/models/tempesthenno--converge-breadcrumbs | |
layer_range: [8, 16] | |
parameters: | |
weight: 0.40 | |
nuslerp_flatten: false | |
nuslerp_row_wise: true | |
- sources: | |
- model: /Users/sthenno/models/tempesthenno--converge-dtask | |
layer_range: [16, 24] | |
parameters: | |
weight: 0.55 | |
nuslerp_flatten: false | |
nuslerp_row_wise: false | |
- model: /Users/sthenno/models/tempesthenno--converge-breadcrumbs | |
layer_range: [16, 24] | |
parameters: | |
weight: 0.45 | |
nuslerp_flatten: false | |
nuslerp_row_wise: false | |
- sources: | |
- model: /Users/sthenno/models/tempesthenno--converge-dtask | |
layer_range: [24, 32] | |
parameters: | |
weight: 0.50 | |
nuslerp_flatten: false | |
nuslerp_row_wise: false | |
- model: /Users/sthenno/models/tempesthenno--converge-breadcrumbs | |
layer_range: [24, 32] | |
parameters: | |
weight: 0.50 | |
nuslerp_flatten: false | |
nuslerp_row_wise: false | |
- sources: | |
- model: /Users/sthenno/models/tempesthenno--converge-dtask | |
layer_range: [32, 40] | |
parameters: | |
weight: 0.45 | |
nuslerp_flatten: true | |
- model: /Users/sthenno/models/tempesthenno--converge-breadcrumbs | |
layer_range: [32, 40] | |
parameters: | |
weight: 0.55 | |
nuslerp_flatten: true | |
- sources: | |
- model: /Users/sthenno/models/tempesthenno--converge-dtask | |
layer_range: [40, 48] | |
parameters: | |
weight: 0.40 | |
nuslerp_flatten: true | |
- model: /Users/sthenno/models/tempesthenno--converge-breadcrumbs | |
layer_range: [40, 48] | |
parameters: | |
weight: 0.60 | |
nuslerp_flatten: true | |