crestf411 commited on
Commit
f491588
·
verified ·
1 Parent(s): ca4c145

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -1
README.md CHANGED
@@ -27,6 +27,13 @@ Recommended starting point:
27
 
28
  At early context, I recommend keeping XTC disabled. Once you hit higher context sizes (10k+), enabling XTC at 0.1 / 0.5 seems to significantly improve the output, but YMMV. If the output drones on and is uninspiring, XTC can be extremely effective.
29
 
 
 
 
 
 
 
 
30
  General heuristic:
31
 
32
  * Lots of slop? Temperature is too low. Raise it, or enable XTC. For early context, temp bump is probably preferred.
@@ -39,7 +46,7 @@ This model has been trained on context that mimics that of Silly Tavern's "Mistr
39
  Silly Tavern output example (Henry is the human, Beth the bot):
40
 
41
  ```
42
- [INST] Henry: I poke Beth.[/INST] Beth: Beth yelps.
43
  ```
44
 
45
  The model has also been trained to do interactive storywriting. You may steer the model towards specific content by "responding" to the model like so:
 
27
 
28
  At early context, I recommend keeping XTC disabled. Once you hit higher context sizes (10k+), enabling XTC at 0.1 / 0.5 seems to significantly improve the output, but YMMV. If the output drones on and is uninspiring, XTC can be extremely effective.
29
 
30
+ *[User](https://huggingface.co/crestf411/MS-sunfall-v0.7.0/discussions/1#672104795c98f6ace037ba61) suggests adding this as an author note/world info In-chat @ Depth '0' is effective:*
31
+
32
+ ```
33
+ [OOC: Guidelines: take into account the character's personality, background, relationships and previous history before intimate scenes. Intimate scenes should have a logical explanation and result from a current or past situation. {{char}} will not submit to {{user}} without good reason.]
34
+ ```
35
+
36
+
37
  General heuristic:
38
 
39
  * Lots of slop? Temperature is too low. Raise it, or enable XTC. For early context, temp bump is probably preferred.
 
46
  Silly Tavern output example (Henry is the human, Beth the bot):
47
 
48
  ```
49
+ [INST] Henry: I poke Beth.[/INST] Beth: Beth yelps.</s>[INST] Henry: ...
50
  ```
51
 
52
  The model has also been trained to do interactive storywriting. You may steer the model towards specific content by "responding" to the model like so: