Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,12 @@ Determine if applying LoRAs and stacking LoRAs onto merged models bypasses the z
|
|
| 25 |
|
| 26 |
The desired result is to additively apply desired features without paradoxically watering down a model's effective behavior.
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
Language Models and LoRAs Used Credits:
|
| 29 |
|
| 30 |
manticore-13b [Epoch3] by openaccess-ai-collective
|
|
|
|
| 25 |
|
| 26 |
The desired result is to additively apply desired features without paradoxically watering down a model's effective behavior.
|
| 27 |
|
| 28 |
+
Results are very promising. Further tests are required.
|
| 29 |
+
|
| 30 |
+
Releasing Chimera as-is; Alpaca instruct verified working, Vicuna instruct formats should work.
|
| 31 |
+
If using KoboldAI or Text-Generation-WebUI, recommend switching between Godlike and Storywriter presets and adjusting output length + instructions in memory.
|
| 32 |
+
Other presets as well as custom settings can yield highly different results as well as Temperature. If poking it with a stick doesn't work try another stick.
|
| 33 |
+
|
| 34 |
Language Models and LoRAs Used Credits:
|
| 35 |
|
| 36 |
manticore-13b [Epoch3] by openaccess-ai-collective
|