sphiratrioth666 commited on
Commit
0a2c809
1 Parent(s): 5c16805

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -21,8 +21,14 @@ Simple, effective, universal presets for Silly Tavern role-playing purposes.
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 "We're presenting a 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 by reading its description page. Different templates may be used by creators (tuners) for training - and then - templates suggested on a fine-tune's page work better. However, creators often just choose the basic template of a model they're tuning - so make sure to check the model's description page or assume it's using the base model's template.
25
-
 
 
 
 
 
 
26
 
27
  *Context Template = Story String*
28
  People often get confused with names.
 
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 "We're presenting a 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 by reading its description page. Different templates may be used by creators (tuners) for training - and then - templates suggested on a fine-tune's page work better. However, creators often just choose the basic template of a model they're tuning - so make sure to check the model's description page or assume it's using the base model's template (template of the main model that a given tuner is tuning).
25
+ ***<<< most typical templates: Mistral, ChatML, Alpaca, Metharme/Pygmalion >>>***/
26
+ 2. Golden Rule: Match CONTEXT TEMPLATE (Story String) and INSTRUCT TEMPLATE with your model. For instance, when Mistral-Nemo fine-tune is using the Mistral Instruct Template (as specified by creator of a fine-tune) - pick up the "Sphiratrioth - Mistral [CONTEXT TEMPLATE]" file and "Sphiratrioth - Mistral [INSTRUCT TEMPLATE]" file. It's very easy. I keep my naming clear - both the file names and preset names inside of the Silly Tavern UI list when you load them up. They're always clear and distinguishable.
27
+ ***<<< this rule may be broken when you become the advanced user. Then, you'll know what you're doing so you'll mix different context/instruct templates. For now - one ring... khem - one template to rule them all. Don't be the Amazon Saur-off. Be a true, Tolkien's Lord of the Templates.>>>***/
28
+ 3. Download my presets.
29
+ 4. Copy the [CONTEXT TEMPLATE] files to (...)\SillyTavern\data\default-user\context
30
+ 5. Copy the [INSTRUCT TEMPLATE] files to (...)\SillyTavern\data\default-user\context
31
+ 6. Copy the [SETTINGS] files to SillyTavern\data\default-user\TextGen Settings
32
 
33
  *Context Template = Story String*
34
  People often get confused with names.