slices: | |
- sources: | |
- model: coldint/10.5B_v1 | |
layer_range: [0, 36] | |
- sources: # add middle layers with residuals scaled to zero | |
- model: coldint/10.5B_v1 | |
layer_range: [34, 36] | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 0.0 | |
- filter: down_proj | |
value: 0.0 | |
- value: 1.0 | |
# - sources: # add middle layers with residuals scaled to zero | |
#- model: upstage/SOLAR-10.7B-v1.0 | |
# layer_range: [14, 24] | |
# parameters: | |
#scale: | |
#- filter: o_proj | |
#value: 0.0 | |
# - filter: down_proj | |
# value: 0.0 | |
# - value: 1.0 | |
- sources: | |
- model: coldint/10.5B_v1 | |
layer_range: [36, 43] | |
merge_method: passthrough | |
dtype: bfloat16 | |