38 lines
881 B
YAML
38 lines
881 B
YAML
|
|
base_model:
|
||
|
|
model:
|
||
|
|
path: Aryanne/Open-StarLake-Swap-7B
|
||
|
|
dtype: bfloat16
|
||
|
|
merge_method: task_swapping
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- layer_range: [0, 32]
|
||
|
|
model:
|
||
|
|
model:
|
||
|
|
path: l3utterfly/mistral-7b-v0.1-layla-v4-chatml
|
||
|
|
parameters:
|
||
|
|
diagonal_offset: 4.0
|
||
|
|
random_mask: 0.1
|
||
|
|
random_mask_seed: 1956557.0
|
||
|
|
weight: 0.4
|
||
|
|
- layer_range: [0, 32]
|
||
|
|
model:
|
||
|
|
model:
|
||
|
|
path: cognitivecomputations/dolphin-2.2.1-mistral-7b
|
||
|
|
parameters:
|
||
|
|
diagonal_offset: 4.0
|
||
|
|
random_mask: 0.1
|
||
|
|
random_mask_seed: 18019.0
|
||
|
|
weight: 0.333
|
||
|
|
- layer_range: [0, 32]
|
||
|
|
model:
|
||
|
|
model:
|
||
|
|
path: teknium/Mistral-Trismegistus-7B
|
||
|
|
parameters:
|
||
|
|
diagonal_offset: 4.0
|
||
|
|
random_mask: 0.05
|
||
|
|
random_mask_seed: 666666.0
|
||
|
|
weight: 0.5
|
||
|
|
- layer_range: [0, 32]
|
||
|
|
model:
|
||
|
|
model:
|
||
|
|
path: Aryanne/Open-StarLake-Swap-7B
|