Update README.md
Browse files
README.md
CHANGED
@@ -12,16 +12,15 @@ Below is a use case example of using Alpac(ino) in either Text-Generation-WebUI
|
|
12 |
Enable chat mode, name the user Player and the AI Narrator, tailor the instructions below as desired and paste in context/memory field-
|
13 |
|
14 |
|
15 |
-
\#\#\# Instruction:
|
16 |
Make Narrator function as a text based adventure game that responds with verbose, detailed, and creative descriptions of what happens next after Player's response.
|
17 |
Make Player function as the player input for Narrator's text based adventure game, controlling a character named (insert character name here, their short bio, and
|
18 |
whatever quest or other information to keep consistent in the interaction).
|
19 |
-
\#\#\# Response:
|
20 |
-
(carriage return after response)
|
21 |
|
22 |
-
Testing subjectively suggests ideal presets
|
23 |
-
|
24 |
-
use half as many tokens
|
25 |
|
26 |
Legalese:
|
27 |
This release contains modified weights from the LLaMA-13b model. This model is under a non-commercial
|
|
|
12 |
Enable chat mode, name the user Player and the AI Narrator, tailor the instructions below as desired and paste in context/memory field-
|
13 |
|
14 |
|
15 |
+
\#\#\# Instruction:(carriage return)
|
16 |
Make Narrator function as a text based adventure game that responds with verbose, detailed, and creative descriptions of what happens next after Player's response.
|
17 |
Make Player function as the player input for Narrator's text based adventure game, controlling a character named (insert character name here, their short bio, and
|
18 |
whatever quest or other information to keep consistent in the interaction).
|
19 |
+
\#\#\# Response:(carriage return)
|
|
|
20 |
|
21 |
+
Testing subjectively suggests ideal presets for both TGUI and KAI are "Storywriter" (temp raised to 1.1) or "Godlike" with context tokens
|
22 |
+
at 2048 and max generation tokens at ~680 or greater. This model is intelligent enough to determine when to stop writing and will rarely
|
23 |
+
use half as many tokens.
|
24 |
|
25 |
Legalese:
|
26 |
This release contains modified weights from the LLaMA-13b model. This model is under a non-commercial
|