Update README.md
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ Should remain usable with only `12GB of VRAM` when quanted to IQ3_M or IQ3_S.
|
|
| 42 |
- MinP: 0.05
|
| 43 |
- Rep Pen: Not needed, but if you do use it keep the range low!
|
| 44 |
- Do not use DRY!
|
| 45 |
-
- System prompt: Trained on Sillytavern defaults. Add `Reason out your answer between the <think> and </think> tags.` to the end of your prompt. Optionally you may wish to prompt the model to have positive bias.
|
| 46 |
- Add the `<think>` tag to the beginning of the response.
|
| 47 |
- Enable reasoning auto-parse, and remove the newlines from the reasoning formatting prefix and suffix.
|
| 48 |
- Q4_K_M is reccomended as the smallest effectively lossless quant.
|
|
|
|
| 42 |
- MinP: 0.05
|
| 43 |
- Rep Pen: Not needed, but if you do use it keep the range low!
|
| 44 |
- Do not use DRY!
|
| 45 |
+
- System prompt: Trained on Sillytavern defaults. Add `Reason out your answer between the <think> and </think> tags.` to the end of your system prompt. Optionally you may wish to prompt the model to have positive bias.
|
| 46 |
- Add the `<think>` tag to the beginning of the response.
|
| 47 |
- Enable reasoning auto-parse, and remove the newlines from the reasoning formatting prefix and suffix.
|
| 48 |
- Q4_K_M is reccomended as the smallest effectively lossless quant.
|