Update README.md
Browse files
README.md
CHANGED
@@ -9,37 +9,41 @@ tags:
|
|
9 |
license: cc-by-nc-4.0
|
10 |
---
|
11 |
|
12 |
-
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6720ed503a24966ac66495e8/
|
13 |
|
14 |
# Starcannon Unleashed 12B v1.0
|
15 |
|
16 |
## Introduction
|
17 |
|
|
|
18 |
## Sample Output
|
19 |
|
|
|
20 |
## Instruct
|
21 |
|
22 |
Both ChatML and Mistral should work fine. Personally, I tested this using ChatML. I found that I like the model's responses better when I use this format. Try to test it out and observe which one you like best. :D
|
23 |
|
|
|
24 |
## Settings
|
25 |
|
26 |
-
I recommend using
|
|
|
27 |
|
28 |
-
|
29 |
-
or
|
30 |
-
[ST-formatting-2024-10-29-02.json](https://huggingface.co/VongolaChouko/Starcannon-Unleashed-12B-v1.0/blob/main/ST-formatting-2024-10-29-02.json)
|
31 |
|
32 |
-
|
33 |
|
34 |
-
|
35 |
|
36 |
Both are modified version of MarinaraSpaghetti's Mistral-Small-Correct.json, transformed into ChatML.
|
37 |
|
38 |
You can find the original version here: [MarinaraSpaghetti/SillyTavern-Settings](https://huggingface.co/MarinaraSpaghetti/SillyTavern-Settings/tree/main/Customized)
|
39 |
|
|
|
40 |
## Tips
|
41 |
|
42 |
-
|
|
|
43 |
|
44 |
|
45 |
## Merge Details
|
|
|
9 |
license: cc-by-nc-4.0
|
10 |
---
|
11 |
|
12 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6720ed503a24966ac66495e8/HXc0AxPLkoIC1fy0Pb3Pb.png)
|
13 |
|
14 |
# Starcannon Unleashed 12B v1.0
|
15 |
|
16 |
## Introduction
|
17 |
|
18 |
+
|
19 |
## Sample Output
|
20 |
|
21 |
+
|
22 |
## Instruct
|
23 |
|
24 |
Both ChatML and Mistral should work fine. Personally, I tested this using ChatML. I found that I like the model's responses better when I use this format. Try to test it out and observe which one you like best. :D
|
25 |
|
26 |
+
|
27 |
## Settings
|
28 |
|
29 |
+
I recommend using these setings:
|
30 |
+
[Starcannon-Unleashed-12B-v1.0-ST-Formatting-2024-10-29.json](https://huggingface.co/VongolaChouko/Starcannon-Unleashed-12B-v1.0/blob/main/ST-formatting-2024-10-29-01.json)
|
31 |
|
32 |
+
**IMPORTANT: Open Silly Tavern and use "Master Import", which can be found under "A" tab — Advanced Formatting. Replace "INSERT WORLD HERE" with the world/universe in which your charcater belongs to. If not applicable, just remove that part.**
|
|
|
|
|
33 |
|
34 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6720ed503a24966ac66495e8/hAr6qvG3iWKKXOUP9Sy07.png)
|
35 |
|
36 |
+
Temperature 1.15 - 1.25 is good, but lower should also work well, as long as you also tweak the Min P and XTC to ensure the model won't choke. Play around with it to see what suits your taste.
|
37 |
|
38 |
Both are modified version of MarinaraSpaghetti's Mistral-Small-Correct.json, transformed into ChatML.
|
39 |
|
40 |
You can find the original version here: [MarinaraSpaghetti/SillyTavern-Settings](https://huggingface.co/MarinaraSpaghetti/SillyTavern-Settings/tree/main/Customized)
|
41 |
|
42 |
+
|
43 |
## Tips
|
44 |
|
45 |
+
- Examples of Dialogue and First Message are very important. The model will copy the style you wrote in these sections, so for example, if you want short outputs, make Examples of Dialogue and First Message short, and so on.
|
46 |
+
- Utilize Author's Note In-chat @ Depth 2 as System if you want the instruction to have greater impact on the next response. If you want something exciting and spontaneous, you can try out this note I added when I tested out the model: "Scenario: Spontaneous. {{char}} has full autonomy to do anything they wish and progress the interaction in any way they like."
|
47 |
|
48 |
|
49 |
## Merge Details
|