miqu-a0-wlfrm-120b / miqu-1-120b-attenuated.yml
froggeric's picture
Upload folder using huggingface_hub
b042843 verified
raw
history blame contribute delete
No virus
2.52 kB
###############################
# miqu-1-120b-attenuated.yaml #
###############################
# Use: mergekit-yaml --clone-tensors ./miqu-1-120b-attenuated.yaml ./miqu-1-120b-attenuated
# See: https://huggingface.co/wolfram/miqu-1-120b for original 'miqu-1-120b' layer ranges.
# See: https://github.com/arcee-ai/mergekit/issues/198 for discussion/reasoning behind this idea.
# ---
# The scale factor to use, eg: solve x^2 = 1/2 --> x = 1/sqrt(2) ≈ 0.7071067812
const_tag: &scale_factor 0.7071067812 # 1/sqrt(2)
# The filter parameters of a scaled block.
attenuate-env: &attenuated_env
parameters:
scale:
- filter: q_proj
value: *scale_factor
- filter: k_proj
value: *scale_factor
- value: 1.0
# ---
slices:
###########################
# Block 1: miqu-1 [0, 20] #
###########################
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 10] # The first 10 layers of Block 1 are not duplicated
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [10, 20] # The last 10 layers of Block 1 are are duplicated twice
<<: *attenuated_env
###########################
# Block 2: miqu-1 [10, 30] #
###########################
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [10, 30]
<<: *attenuated_env
###########################
# Block 3: miqu-1 [20, 40] #
###########################
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [20, 40]
<<: *attenuated_env
###########################
# Block 4: miqu-1 [30, 50] #
###########################
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [30, 50]
<<: *attenuated_env
###########################
# Block 5: miqu-1 [40, 60] #
###########################
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [40, 60]
<<: *attenuated_env
###########################
# Block 6: miqu-1 [50, 70] #
###########################
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [50, 70]
<<: *attenuated_env
##########################
# Block 7: miqu-1 [60, 80] #
##########################
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [60, 70] # The first 10 layers of Block 7 are are duplicated twice
<<: *attenuated_env
- sources:
- model: 152334H/miqu-1-70b-sf
layer_range: [70, 80] # The last 10 layers of Block 7 are not duplicated
merge_method: passthrough
dtype: float16