ToastyPigeon
commited on
Commit
•
f3975e7
1
Parent(s):
b78ff30
Update README.md
Browse files
README.md
CHANGED
@@ -23,4 +23,12 @@ I tried different blends of the component models, and this one seems to be the m
|
|
23 |
# Instruct Format
|
24 |
Rosier/bodyinf and SpringDragon were trained in completion format. This model should work with [Kobold Lite](https://lite.koboldai.net/) in Adventure Mode and Story Mode.
|
25 |
|
26 |
-
Creative_Writing_Multiturn
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
# Instruct Format
|
24 |
Rosier/bodyinf and SpringDragon were trained in completion format. This model should work with [Kobold Lite](https://lite.koboldai.net/) in Adventure Mode and Story Mode.
|
25 |
|
26 |
+
Creative_Writing_Multiturn was trained using the official instruct format of Mistral Small Instruct:
|
27 |
+
```
|
28 |
+
<s>[INST] {User message}[/INST] {Assistant response}</s>[INST] {Optional system prompt}
|
29 |
+
|
30 |
+
{User message}[/INST] {Assistant response}</s>
|
31 |
+
```
|
32 |
+
This is the Mistral Small V2&V3 preset in SillyTavern and Kobold Lite.
|
33 |
+
|
34 |
+
For SillyTavern in particular I've had better luck getting good output from Mistral Small using a [custom instruct template](https://huggingface.co/ToastyPigeon/ST-Presets-Mistral-Small) that formats the assembled context as a single user turn. This prevents SillyTavern from confusing the model by assembling user/assistant turns in a nonstandard way.
|