abdullahalzubaer commited on
Commit
a83c755
·
verified ·
1 Parent(s): 1a0658c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -15,6 +15,9 @@ abdullah-Qwen-Qwen2.5-0.5B-Instruct-merged-two-same-model-slerp is a merge of th
15
 
16
  ## 🧩 Configuration
17
 
 
 
 
18
  ```yaml
19
  slices:
20
  - sources:
@@ -77,6 +80,12 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
77
  ```
78
 
79
 
 
 
 
 
 
 
80
 
81
  ## Citation
82
 
 
15
 
16
  ## 🧩 Configuration
17
 
18
+ Note: You nedd to change the layer range based on `number of layers` in the model. For `Qwen/Qwen2.5-0.5B-Instruct` number of layer is 24. The notebook used (see below in reference section
19
+ had `layer_range` `[0, 32]`, this is not true for the qwen model I am using here)
20
+
21
  ```yaml
22
  slices:
23
  - sources:
 
80
  ```
81
 
82
 
83
+ ## Reference:
84
+
85
+ Used this https://huggingface.co/blog/mlabonne/merge-models for creating the merged model
86
+
87
+
88
+
89
 
90
  ## Citation
91