3Blarenegv3 ECE PRYMMAL Martial
50
20
3.0B
license:apache-2.0
by
brgx53
Language Model
OTHER
3B params
New
50 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
7GB+ RAM
Mobile
Laptop
Server
Quick Summary
AI model with specialized capabilities.
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
3GB+ RAM
Code Examples
Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Configurationyaml
slices:
- sources:
- model: fblgit/cybertron-v4-qw7B-MGS
layer_range: [0, 28]
- model: Tsunami-th/Tsunami-0.5x-7B-Instruct
layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
t:
- filter: self_attn
value: [1, 0.75, 0.5, 0.25, 0]
- filter: mlp
value: [0, 0.25, 0.5, 0.75, 1]
- value: 0.5
dtype: bfloat16Deploy 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.