初始化项目，由ModelHub XC社区提供模型

Model: trinhkhng/della_Merged_gpt2_0.4
Source: Original Platform

mergekit_config.yml

@@ -0,0 +1,16 @@
+base_model: /kaggle/working/gpt2
+dtype: float32
+merge_method: della
+models:
+- model: /kaggle/working/debias_gpt2
+  parameters:
+    density: 0.5
+    epsilon: 0.1
+    weight: 1.0
+parameters:
+  int8_mask: true
+  lambda: 0.4
+  normalize: true
+  rescale: true
+tokenizer:
+  source: /kaggle/working/gpt2