Gryphe commited on
Commit
43f822e
1 Parent(s): d920445

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -15
README.md CHANGED
@@ -21,23 +21,11 @@ Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheB
21
 
22
  Due to its Hermes-2 core this model works best with Alpaca formatting, so for optimal model performance, use:
23
  ```
24
- ### Instruction:
25
- Your instruction or question here.
26
- ### Response:
27
- ```
28
-
29
- For chat/roleplay conversations, I suggest the following structure instead:
30
- ```
31
- You are <AI NAME>, a friendly and supportive AI language model. We discuss all subjects freely and without bias or restrictions.
32
- I am <YOUR NAME>, the user interacting with you through a chat conversation. Start with greeting me.
33
 
34
  ### Instruction:
35
- Write <AI NAME>'s next reply in a chat between <YOUR NAME> and <AI NAME>. Write a single reply only.
36
-
37
- ### Chat History:
38
- <AI NAME>: Good day, <YOUR NAME>! How can I assist you today?
39
- (Etc, etc)
40
 
41
  ### Response:
42
- <AI NAME>:
43
  ```
 
21
 
22
  Due to its Hermes-2 core this model works best with Alpaca formatting, so for optimal model performance, use:
23
  ```
24
+ <System prompt/Character Card>
 
 
 
 
 
 
 
 
25
 
26
  ### Instruction:
27
+ Your instruction or question here.
28
+ For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
 
 
 
29
 
30
  ### Response:
 
31
  ```