Update README.md
Browse files
README.md
CHANGED
@@ -19,23 +19,11 @@ Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheB
|
|
19 |
|
20 |
This model works best with Alpaca formatting, so for optimal model performance, use:
|
21 |
```
|
22 |
-
|
23 |
-
Your instruction or question here.
|
24 |
-
### Response:
|
25 |
-
```
|
26 |
-
|
27 |
-
For chat/roleplay conversations, I suggest the following structure instead:
|
28 |
-
```
|
29 |
-
You are <AI NAME>, a friendly and supportive AI language model. We discuss all subjects freely and without bias or restrictions.
|
30 |
-
I am <YOUR NAME>, the user interacting with you through a chat conversation. Start with greeting me.
|
31 |
|
32 |
### Instruction:
|
33 |
-
|
34 |
-
|
35 |
-
### Chat History:
|
36 |
-
<AI NAME>: Good day, <YOUR NAME>! How can I assist you today?
|
37 |
-
(Etc, etc)
|
38 |
|
39 |
### Response:
|
40 |
-
<AI NAME>:
|
41 |
```
|
|
|
19 |
|
20 |
This model works best with Alpaca formatting, so for optimal model performance, use:
|
21 |
```
|
22 |
+
<System prompt/Character Card>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
### Instruction:
|
25 |
+
Your instruction or question here.
|
26 |
+
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.
|
|
|
|
|
|
|
27 |
|
28 |
### Response:
|
|
|
29 |
```
|