nimbus
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Passthrough merge method.
Models Merged
The following models were included in the merge:
- merge/wind
Configuration
The following YAML configuration was used to produce this model:
dtype: float32
merge_method: passthrough
modules:
default:
slices:
- sources:
- layer_range: [0, 4]
model: merge/wind
- sources:
- layer_range: [2, 4]
model: merge/wind
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [4, 6]
model: merge/wind
- sources:
- layer_range: [4, 6]
model: merge/wind
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [6, 8]
model: merge/wind
- sources:
- layer_range: [6, 8]
model: merge/wind
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [8, 10]
model: merge/wind
- sources:
- layer_range: [8, 10]
model: merge/wind
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [10, 14]
model: merge/wind
- sources:
- layer_range: [12, 14]
model: merge/wind
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [14, 18]
model: merge/wind
- sources:
- layer_range: [16, 18]
model: merge/wind
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [18, 28]
model: merge/wind
- sources:
- layer_range: [26, 28]
model: merge/wind
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [28, 30]
model: merge/wind
- sources:
- layer_range: [28, 30]
model: merge/wind
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [30, 32]
model: merge/wind
- sources:
- layer_range: [30, 32]
model: merge/wind
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- Downloads last month
- 10