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
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 |