Files
l3.0-upscale-1/mergekit_config.yml

60 lines
1.4 KiB
YAML
Raw Normal View History

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
# 816 baseline
- sources:
- layer_range: [8, 12]
model: meta-llama/Meta-Llama-3-8B
# 816 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
# 1624 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
# 1624 baseline
- sources:
- layer_range: [16, 24]
model: meta-llama/Meta-Llama-3-8B
# 1624 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