23 lines
663 B
YAML
23 lines
663 B
YAML
|
models:
|
||
|
|
- model: Qwen/Qwen3-1.7B
|
||
|
|
- model: /scratch/final_project/code/group_model/models/Qwen3-1.7B-math
|
||
|
|
parameters:
|
||
|
|
density: 0.53
|
||
|
|
weight: 0.35
|
||
|
|
- model: /scratch/final_project/code/group_model/models/Qwen3-1.7B-general
|
||
|
|
parameters:
|
||
|
|
density: 0.53
|
||
|
|
weight: 0.25
|
||
|
|
- model: /scratch/final_project/code/group_model/models/Qwen3-1.7B-multilingual
|
||
|
|
parameters:
|
||
|
|
density: 0.53
|
||
|
|
weight: 0.25
|
||
|
|
- model: /scratch/final_project/code/group_model/models/Qwen3-1.7B-safety
|
||
|
|
parameters:
|
||
|
|
density: 0.53
|
||
|
|
weight: 0.15
|
||
|
|
merge_method: dare_ties
|
||
|
|
base_model: Qwen/Qwen3-1.7B
|
||
|
|
parameters:
|
||
|
|
int8_mask: true
|
||
|
|
dtype: bfloat16
|