ECE-TW3-JRGL-V1
8.5K
1
llama
by
paloalma
Language Model
OTHER
70B params
New
8K downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
157GB+ RAM
Mobile
Laptop
Server
Quick Summary
- Louis Garcia, engineering student at French Engineering School ECE - Matthieu Jollard, engineering student at French Engineering School ECE - Andre-Louis Roc...
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
66GB+ RAM
Code Examples
yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16yaml
slices:
- sources:
- model: ShinojiResearch/Senku-70B-Full
layer_range: [0, 80]
- model: 152334H/miqu-1-70b-sf
layer_range: [0, 80]
merge_method: slerp
base_model: 152334H/miqu-1-70b-sf
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16Deploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.