60 lines
1.4 KiB
YAML
60 lines
1.4 KiB
YAML
|
|
dtype: bfloat16
|
|||
|
|
merge_method: passthrough
|
|||
|
|
|
|||
|
|
slices:
|
|||
|
|
# untouched intro
|
|||
|
|
- sources:
|
|||
|
|
- layer_range: [0, 8]
|
|||
|
|
model: meta-llama/Meta-Llama-3-8B
|
|||
|
|
|
|||
|
|
- sources:
|
|||
|
|
- layer_range: [8, 10]
|
|||
|
|
model: meta-llama/Meta-Llama-3-8B
|
|||
|
|
# 8–16 baseline
|
|||
|
|
- sources:
|
|||
|
|
- layer_range: [8, 12]
|
|||
|
|
model: meta-llama/Meta-Llama-3-8B
|
|||
|
|
# 8–16 duplicate with projections nulled
|
|||
|
|
- sources:
|
|||
|
|
- layer_range: [8, 16]
|
|||
|
|
model: meta-llama/Meta-Llama-3-8B
|
|||
|
|
parameters:
|
|||
|
|
scale:
|
|||
|
|
- filter: o_proj
|
|||
|
|
value: 0.0
|
|||
|
|
- filter: down_proj
|
|||
|
|
value: 0.0
|
|||
|
|
- value: 1.0
|
|||
|
|
|
|||
|
|
# 16–24 duplicate
|
|||
|
|
- sources:
|
|||
|
|
- layer_range: [16, 20]
|
|||
|
|
model: meta-llama/Meta-Llama-3-8B
|
|||
|
|
parameters:
|
|||
|
|
scale:
|
|||
|
|
- filter: o_proj
|
|||
|
|
value: 0.0
|
|||
|
|
- filter: down_proj
|
|||
|
|
value: 0.0
|
|||
|
|
- value: 1.0
|
|||
|
|
# 16–24 baseline
|
|||
|
|
- sources:
|
|||
|
|
- layer_range: [16, 24]
|
|||
|
|
model: meta-llama/Meta-Llama-3-8B
|
|||
|
|
# 16–24 duplicate
|
|||
|
|
- sources:
|
|||
|
|
- layer_range: [16, 20]
|
|||
|
|
model: meta-llama/Meta-Llama-3-8B
|
|||
|
|
parameters:
|
|||
|
|
scale:
|
|||
|
|
- filter: o_proj
|
|||
|
|
value: 0.0
|
|||
|
|
- filter: down_proj
|
|||
|
|
value: 0.0
|
|||
|
|
- value: 1.0
|
|||
|
|
|
|||
|
|
# untouched tail
|
|||
|
|
- sources:
|
|||
|
|
- layer_range: [24, 32]
|
|||
|
|
model: meta-llama/Meta-Llama-3-8B
|