初始化项目,由ModelHub XC社区提供模型
Model: cs-552-2026-databand/group_model Source: Original Platform
This commit is contained in:
32
mergekit_config.yml
Normal file
32
mergekit_config.yml
Normal file
@@ -0,0 +1,32 @@
|
||||
base_model: Qwen/Qwen3-1.7B
|
||||
dtype: bfloat16
|
||||
merge_method: dare_ties
|
||||
modules:
|
||||
default:
|
||||
slices:
|
||||
- sources:
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/math_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/general_knowledge_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/safety_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: cs-552-2026-databand/multilingual_model
|
||||
parameters:
|
||||
density: 0.9
|
||||
weight: 1.0
|
||||
- layer_range: [0, 28]
|
||||
model: Qwen/Qwen3-1.7B
|
||||
parameters:
|
||||
int8_mask: 1.0
|
||||
normalize: 1.0
|
||||
Reference in New Issue
Block a user