sphiratrioth666 commited on
Commit
94a5a06
1 Parent(s): c0928db

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -5,7 +5,7 @@ language:
5
  ---
6
  Simple, effective, universal presets for Silly Tavern role-playing purposes.
7
 
8
- **CONTEXT TEMPLATE (STORY STRING) + INSTRUCT TEMPLATE + SETTINGS (SAMPLERS)**
9
 
10
  **A) Sphiratrioth (Short)** - minimal narration - when you want to simulate a natural, human-like conversation with a bot. For those who do not like the "verbose" role-play.
11
  ***<<< conversation-like, ~ 150 tokens, around 2/3 dialogue against 1/3 narration >>>***
@@ -18,7 +18,10 @@ Simple, effective, universal presets for Silly Tavern role-playing purposes.
18
 
19
  **How to use:**
20
 
21
- 1. Find your LLM (model) native instruct template. Every fine-tune stands on a base model, which is usually specified by its creator. In result, each fine-tune (model you are actually using assuming it's not the raw, base version) should generally work with its original model's instruct template best. However, it's often not the case. Different templates may be used by creators (tuners) in training and theoretically "wrong" templates sometimes provide better role-play results.
 
 
 
22
 
23
 
24
  *Context Template = Story String*
 
5
  ---
6
  Simple, effective, universal presets for Silly Tavern role-playing purposes.
7
 
8
+ **What is included: CONTEXT TEMPLATE (STORY STRING) + INSTRUCT TEMPLATE + SETTINGS (SAMPLERS)**
9
 
10
  **A) Sphiratrioth (Short)** - minimal narration - when you want to simulate a natural, human-like conversation with a bot. For those who do not like the "verbose" role-play.
11
  ***<<< conversation-like, ~ 150 tokens, around 2/3 dialogue against 1/3 narration >>>***
 
18
 
19
  **How to use:**
20
 
21
+ Advanced Users: Load them up under a "capital A" tab (AI Response Formatting) of the Silly Tavern UI. Enjoy, modify, forget.
22
+ Beginner Users: Read further. Those templates should provide what you're looking for.
23
+
24
+ 1. Find your LLM (model) native instruct template. Every fine-tune stands on a base model, which is usually specified by its creator in a manner of "(...) fine-tune of Mistral Small" or "Nemo on steroids" etc. It may be confusing, it may be clear. Not my fault :-P However, you need to identify the base model of a fine-tune- since it will generally work with its original model's context/instruct templates best. However, different templates may be used by creators (tuners) for training and then - specified templates suggested by creators work better. Now - brace yourself, it's funny - sometimes, theoretically "wrong" templates provide even better role-play results.
25
 
26
 
27
  *Context Template = Story String*