VongolaChouko commited on
Commit
17e908f
·
verified ·
1 Parent(s): e00621d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -8
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/ZpGMh2ksjbx9d04P-IduI.png)
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 either of these setings:
 
27
 
28
- [ST-formatting-2024-10-29-01.json](https://huggingface.co/VongolaChouko/Starcannon-Unleashed-12B-v1.0/blob/main/ST-formatting-2024-10-29-01.json)
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
- **IMPORTANT: Master Import in Silly Tavern. Replace "INSERT WORLD HERE" with the world/universe in which your charcater belongs to. If not applicable, just remove that part.**
33
 
34
- The only difference between the two are their Temperature settings. Again, play around with it to see what suits your taste.
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
- 1. Example Messeges I find that it's very important and the model really does copy what it's given, so if you want short outputs, make the first message and example messages short, and so on.
 
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