初始化项目,由ModelHub XC社区提供模型
Model: Lambent/Qwen3-4B-Base-Continued-GRPO-Merge Source: Original Platform
This commit is contained in:
9
mergekit_config.yml
Normal file
9
mergekit_config.yml
Normal file
@@ -0,0 +1,9 @@
|
||||
# TIES merge: Judge as base, inject sparse GRPO knowledge
|
||||
merge_method: ties
|
||||
base_model: ./merged_models/llm-judge-merged-fixed
|
||||
models:
|
||||
- model: ./merged_models/grpo-cabs
|
||||
parameters:
|
||||
density: 0.5
|
||||
weight: 0.4
|
||||
dtype: bfloat16
|
||||
Reference in New Issue
Block a user