Update README.md
Browse files
README.md
CHANGED
|
@@ -11,9 +11,7 @@ tags:
|
|
| 11 |
|
| 12 |
## Details
|
| 13 |
|
| 14 |
-
The control-vectors in this repo were created as an experiment by increasing the triplets in `system_messages_outlook_extended.json` by 4x
|
| 15 |
-
|
| 16 |
-
This means each models' cross-covariance matrix will be the result of `120,000` hidden state samples and this in turn will mean each uses ~10x the hidden state dimension for the largest models (click to expand):
|
| 17 |
|
| 18 |
<details> <summary>"Outlook (extended)" ('positive' <---> 'negative')</summary>
|
| 19 |
|
|
@@ -150,6 +148,8 @@ This means each models' cross-covariance matrix will be the result of `120,000`
|
|
| 150 |
|
| 151 |
</details>
|
| 152 |
|
|
|
|
|
|
|
| 153 |
## Regularisation
|
| 154 |
|
| 155 |
I also include 3 different values for the `--regularisation_factor` option; `1.0` (the default), `0.5` and `0.0`:
|
|
|
|
| 11 |
|
| 12 |
## Details
|
| 13 |
|
| 14 |
+
The control-vectors in this repo were created as an experiment by increasing the triplets in `system_messages_outlook_extended.json` by 4x (click to expand):
|
|
|
|
|
|
|
| 15 |
|
| 16 |
<details> <summary>"Outlook (extended)" ('positive' <---> 'negative')</summary>
|
| 17 |
|
|
|
|
| 148 |
|
| 149 |
</details>
|
| 150 |
|
| 151 |
+
This means each models' cross-covariance matrix will be the result of `120,000` hidden state samples and this in turn will mean each uses ~10x the hidden state dimension for the largest models.
|
| 152 |
+
|
| 153 |
## Regularisation
|
| 154 |
|
| 155 |
I also include 3 different values for the `--regularisation_factor` option; `1.0` (the default), `0.5` and `0.0`:
|