Weyaxi commited on
Commit
7e180a1
1 Parent(s): bf9ef6d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -0
README.md CHANGED
@@ -2,10 +2,37 @@
2
  ---
3
  license: apache-2.0
4
  ---
 
 
5
  # OpenHermes-2.5-neural-chat-v3-2-Slerp
6
 
7
  This is the model for OpenHermes-2.5-neural-chat-v3-2-Slerp. I used [mergekit](https://github.com/cg123/mergekit) to merge models.
8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  # Yaml Config to reproduce
10
 
11
  ```yaml
@@ -28,3 +55,5 @@ parameters:
28
  dtype: float16
29
 
30
  ```
 
 
 
2
  ---
3
  license: apache-2.0
4
  ---
5
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/x44nNbPTpv0zGTqA1Jb2q.png)
6
+
7
  # OpenHermes-2.5-neural-chat-v3-2-Slerp
8
 
9
  This is the model for OpenHermes-2.5-neural-chat-v3-2-Slerp. I used [mergekit](https://github.com/cg123/mergekit) to merge models.
10
 
11
+ # Prompt Templates
12
+
13
+ You can use these prompt templates, but I recommend using ChatML.
14
+
15
+ ### ChatML [(OpenHermes-2.5-Mistral-7B)](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B):
16
+
17
+ ```
18
+ <|im_start|>system
19
+ {system}<|im_end|>
20
+ <|im_start|>user
21
+ {user}<|im_end|>
22
+ <|im_start|>assistant
23
+ {asistant}<|im_end|>
24
+ ```
25
+
26
+ ### [neural-chat-7b-v3-2](https://huggingface.co/Intel/neural-chat-7b-v3-2):
27
+
28
+ ```
29
+ ### System:
30
+ {system}
31
+ ### User:
32
+ {user}
33
+ ### Assistant:
34
+ ```
35
+
36
  # Yaml Config to reproduce
37
 
38
  ```yaml
 
55
  dtype: float16
56
 
57
  ```
58
+
59
+