Update README.md
Browse files
README.md
CHANGED
@@ -21,11 +21,14 @@ The desired outcome is to additively apply desired features without paradoxicall
|
|
21 |
|
22 |
Potential limitations - LoRAs applied on top of each other may intercompete.
|
23 |
|
24 |
-
Subjective results
|
25 |
|
26 |
-
|
|
|
|
|
27 |
If using KoboldAI or Text-Generation-WebUI, recommend switching between Godlike and Storywriter presets and adjusting output length + instructions in memory.
|
28 |
-
Other presets as well as custom settings can yield highly different results
|
|
|
29 |
|
30 |
## Language Models and LoRAs Used Credits:
|
31 |
|
|
|
21 |
|
22 |
Potential limitations - LoRAs applied on top of each other may intercompete.
|
23 |
|
24 |
+
Subjective results - very promising. Further tests are required to include isolated tests and benchmarking (exact method not determined at this time).
|
25 |
|
26 |
+
Instruct and Setup Suggestions:
|
27 |
+
|
28 |
+
Alpaca instruct verified working, Vicuna instruct formats should work.
|
29 |
If using KoboldAI or Text-Generation-WebUI, recommend switching between Godlike and Storywriter presets and adjusting output length + instructions in memory.
|
30 |
+
Other presets as well as custom settings can yield highly different results, especially Temperature.
|
31 |
+
If poking it with a stick doesn't work try another stick.
|
32 |
|
33 |
## Language Models and LoRAs Used Credits:
|
34 |
|