Text Generation
Transformers
Safetensors
qwen3_moe
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prose
vivid writing
Mixture of Experts
mixture of experts
128 experts
8 active experts
fiction
roleplaying
bfloat16
rp
qwen3
horror
finetune
thinking
reasoning
conversational
metadata
base_model: []
library_name: transformers
tags:
- mergekit
- merge
Qwen3-30B-A3B-Quake-pass2-bs20-2
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Passthrough merge method.
Models Merged
The following models were included in the merge:
- D:/Qwen3-30B-A3B
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [0, 47]
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.01
- filter: down_proj
value: 0.01
- value: 0.01
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.02
- filter: down_proj
value: 0.02
- value: 0.02
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.03
- filter: down_proj
value: 0.03
- value: 0.03
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.04
- filter: down_proj
value: 0.04
- value: 0.04
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.05
- filter: down_proj
value: 0.05
- value: 0.05
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.06
- filter: down_proj
value: 0.06
- value: 0.06
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.07
- filter: down_proj
value: 0.07
- value: 0.07
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.08
- filter: down_proj
value: 0.08
- value: 0.08
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.09
- filter: down_proj
value: 0.09
- value: 0.09
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.10
- filter: down_proj
value: 0.10
- value: 0.10
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.11
- filter: down_proj
value: 0.11
- value: .20
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.12
- filter: down_proj
value: 0.12
- value: .21
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.13
- filter: down_proj
value: 0.13
- value: .22
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.14
- filter: down_proj
value: 0.14
- value: .23
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.15
- filter: down_proj
value: 0.15
- value: .24
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.16
- filter: down_proj
value: 0.16
- value: .4
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.20
- filter: down_proj
value: 0.20
- value: .5
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.25
- filter: down_proj
value: 0.25
- value: .6
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.30
- filter: down_proj
value: 0.30
- value: .7
- sources:
- model: D:/Qwen3-30B-A3B
layer_range: [47, 48]
parameters:
scale:
- filter: o_proj
value: 0.40
- filter: down_proj
value: 0.40
- value: .8
merge_method: passthrough
dtype: bfloat16