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:
ModelHub XC
2026-06-02 03:31:25 +08:00
commit 913020eb1c
14 changed files with 151950 additions and 0 deletions

9
mergekit_config.yml Normal file
View 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