jerrimu commited on
Commit
8479bdd
·
verified ·
1 Parent(s): fc9dc0b

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +37 -0
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - google/gemma-3-4b-it
8
+ - Qwen/Qwen2.5-Coder-7B
9
+ ---
10
+
11
+ # CodeGem
12
+
13
+ CodeGem is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)
15
+ * [Qwen/Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ slices:
21
+ - sources:
22
+ - model: google/gemma-3-4b-it
23
+ layer_range: [0, 32]
24
+ - model: Qwen/Qwen2.5-Coder-7B
25
+ layer_range: [0, 32]
26
+ merge_method: slerp
27
+ base_model: google/gemma-3-4b-it
28
+ parameters:
29
+ t:
30
+ - filter: self_attn
31
+ value: [0, 0.5, 0.3, 0.7, 1]
32
+ - filter: mlp
33
+ value: [1, 0.5, 0.7, 0.3, 0]
34
+ - value: 0.5
35
+ dtype: bfloat16
36
+
37
+ ```