Update README.md
Browse files
README.md
CHANGED
|
@@ -70,4 +70,8 @@ A batch size of 1 was used because I ~~am GPU-poor~~ have 12GB of VRAM (RTX 3060
|
|
| 70 |
|
| 71 |
|
| 72 |
And **none of the dataset** was used for evaluation loss, which was turned off entirely. It's too small of a dataset to be a meaningful metric, I assume. (I manually tested two merges at different points instead).
|
| 73 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
|
| 72 |
And **none of the dataset** was used for evaluation loss, which was turned off entirely. It's too small of a dataset to be a meaningful metric, I assume. (I manually tested two merges at different points instead).
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
# Notice for SillyTavern users
|
| 76 |
+
The typical Alpaca format that has `### Instruction` and `### Response` will literally interpret what you say as an instruction in a character chat. I would recommend changing this to have the character names instead, e.g `{{user}}` in place of Instruction, and `{{char}}` in place of Response.
|
| 77 |
+
That seemed to improve results as a result, and the character card is also followed well.
|