Update README.md
Browse files
README.md
CHANGED
|
@@ -106,6 +106,9 @@ If you don't like it, **you can override** by editing the character message and
|
|
| 106 |
|
| 107 |
I have tested these settings and they work OK for 16K. Depending on the roleplay complexity and message length, experiment with if the model starts breaking or not. For me, 16K works fine.
|
| 108 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/630cf5d14ca0a22768bbe10c/3f7JOEnXhKCDcDF4Eiq-B.png" alt="" width="300"/>
|
|
|
|
|
|
|
|
|
|
| 109 |
<h2>Other Important Tips</h2>
|
| 110 |
|
| 111 |
Take active role in the RP and say the type of response you expect. You don't always have to do this, but it helps sometimes. For example instead of *we drink and drink 15 glasses of champagne* say *we drink and drink 15 glasses of champagne, both becoming extremely drunk*
|
|
|
|
| 106 |
|
| 107 |
I have tested these settings and they work OK for 16K. Depending on the roleplay complexity and message length, experiment with if the model starts breaking or not. For me, 16K works fine.
|
| 108 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/630cf5d14ca0a22768bbe10c/3f7JOEnXhKCDcDF4Eiq-B.png" alt="" width="300"/>
|
| 109 |
+
<h2>OOC Steering</h2>
|
| 110 |
+
|
| 111 |
+
We specifically trained the model to accept instructions in the format "OOC: character should be more assertive" etc. Even thousands of tokens deep into the context. Combining this with editing the output, the model is very steerable.
|
| 112 |
<h2>Other Important Tips</h2>
|
| 113 |
|
| 114 |
Take active role in the RP and say the type of response you expect. You don't always have to do this, but it helps sometimes. For example instead of *we drink and drink 15 glasses of champagne* say *we drink and drink 15 glasses of champagne, both becoming extremely drunk*
|