206 lines
5.5 KiB
YAML
206 lines
5.5 KiB
YAML
|
|
base_model: ./evolve_storage/input_models/Qwen3-4B_131373129
|
||
|
|
dtype: bfloat16
|
||
|
|
merge_method: ties
|
||
|
|
parameters:
|
||
|
|
int8_mask: 1.0
|
||
|
|
normalize: 1.0
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- layer_range: [0, 6]
|
||
|
|
model: ./evolve_storage/input_models/4b_1_2932744254
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 1.0
|
||
|
|
- filter: self_attn
|
||
|
|
value: 1.0
|
||
|
|
- value: 0.8608594704318231
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.3490062747244206
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.09060462688545917
|
||
|
|
- value: 0.7576223803340598
|
||
|
|
- layer_range: [0, 6]
|
||
|
|
model: ./evolve_storage/input_models/4b_2_935817604
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.9307034739117228
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.7266676131372826
|
||
|
|
- value: 0.7992834608507406
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.02382702396781508
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.19373265930727943
|
||
|
|
- value: 0.5095495553391711
|
||
|
|
- layer_range: [0, 6]
|
||
|
|
model: ./evolve_storage/input_models/Qwen3-4B_131373129
|
||
|
|
- sources:
|
||
|
|
- layer_range: [6, 12]
|
||
|
|
model: ./evolve_storage/input_models/4b_1_2932744254
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 1.0
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.9956934876179888
|
||
|
|
- value: 1.0
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.7637369917121993
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.7579899664980693
|
||
|
|
- value: 0.369874736821347
|
||
|
|
- layer_range: [6, 12]
|
||
|
|
model: ./evolve_storage/input_models/4b_2_935817604
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 1.0
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.7931662945197395
|
||
|
|
- value: 1.0
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.05065405710236617
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.1681017405390699
|
||
|
|
- value: 0.278174377018312
|
||
|
|
- layer_range: [6, 12]
|
||
|
|
model: ./evolve_storage/input_models/Qwen3-4B_131373129
|
||
|
|
- sources:
|
||
|
|
- layer_range: [12, 18]
|
||
|
|
model: ./evolve_storage/input_models/4b_1_2932744254
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 1.0
|
||
|
|
- filter: self_attn
|
||
|
|
value: 1.0
|
||
|
|
- value: 1.0
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.1896079785687373
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.28109871222289246
|
||
|
|
- value: 0.5919682098365076
|
||
|
|
- layer_range: [12, 18]
|
||
|
|
model: ./evolve_storage/input_models/4b_2_935817604
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.9657611673995403
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.7203176611210709
|
||
|
|
- value: 0.5429222666986293
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.6105068874861986
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.35883124159464513
|
||
|
|
- value: 0.08904009475761779
|
||
|
|
- layer_range: [12, 18]
|
||
|
|
model: ./evolve_storage/input_models/Qwen3-4B_131373129
|
||
|
|
- sources:
|
||
|
|
- layer_range: [18, 24]
|
||
|
|
model: ./evolve_storage/input_models/4b_1_2932744254
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.9149303352862976
|
||
|
|
- filter: self_attn
|
||
|
|
value: 1.0
|
||
|
|
- value: 0.877602461891939
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.4686086798952363
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.9038594427840757
|
||
|
|
- value: 0.10082926037736678
|
||
|
|
- layer_range: [18, 24]
|
||
|
|
model: ./evolve_storage/input_models/4b_2_935817604
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.7101112464063535
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.7817731468186313
|
||
|
|
- value: 0.39642301784045736
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.12881047196006434
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.5913495175648413
|
||
|
|
- value: 0.4608092365074321
|
||
|
|
- layer_range: [18, 24]
|
||
|
|
model: ./evolve_storage/input_models/Qwen3-4B_131373129
|
||
|
|
- sources:
|
||
|
|
- layer_range: [24, 30]
|
||
|
|
model: ./evolve_storage/input_models/4b_1_2932744254
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.5207504504970493
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.7016905835163534
|
||
|
|
- value: 0.7841906098086426
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.03936529169370809
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.3540197424712478
|
||
|
|
- value: 0.23794897877129362
|
||
|
|
- layer_range: [24, 30]
|
||
|
|
model: ./evolve_storage/input_models/4b_2_935817604
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.6658594462559264
|
||
|
|
- filter: self_attn
|
||
|
|
value: 1.0
|
||
|
|
- value: 0.7557856184584113
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.5961021443524465
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.5159043688030769
|
||
|
|
- value: 0.7605556292871718
|
||
|
|
- layer_range: [24, 30]
|
||
|
|
model: ./evolve_storage/input_models/Qwen3-4B_131373129
|
||
|
|
- sources:
|
||
|
|
- layer_range: [30, 36]
|
||
|
|
model: ./evolve_storage/input_models/4b_1_2932744254
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 1.0
|
||
|
|
- filter: self_attn
|
||
|
|
value: 1.0
|
||
|
|
- value: 0.63120667056331
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.15069904386157829
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.6308542464264801
|
||
|
|
- value: 0.4804838636683506
|
||
|
|
- layer_range: [30, 36]
|
||
|
|
model: ./evolve_storage/input_models/4b_2_935817604
|
||
|
|
parameters:
|
||
|
|
density:
|
||
|
|
- filter: mlp
|
||
|
|
value: 1.0
|
||
|
|
- filter: self_attn
|
||
|
|
value: 1.0
|
||
|
|
- value: 0.924178196118008
|
||
|
|
weight:
|
||
|
|
- filter: mlp
|
||
|
|
value: 0.5716878395339086
|
||
|
|
- filter: self_attn
|
||
|
|
value: 0.19598590068808175
|
||
|
|
- value: 0.8797652412255632
|
||
|
|
- layer_range: [30, 36]
|
||
|
|
model: ./evolve_storage/input_models/Qwen3-4B_131373129
|