Update README.md
Browse files
README.md
CHANGED
|
@@ -19,4 +19,8 @@ Created by running a high-r LoRA-pass over Nemo-Base with 2 epochs of some RP da
|
|
| 19 |
|
| 20 |
## Prompting
|
| 21 |
|
| 22 |
-
Use the `Mistral V3-Tekken` context- and instruct-templates. Temperature at about `1.25` seems to be the sweet spot, with either MinP at `0.05` or TopP at `0.9`. DRY/Smoothing etc depending on your preference.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Prompting
|
| 21 |
|
| 22 |
+
Use the `Mistral V3-Tekken` context- and instruct-templates. Temperature at about `1.25` seems to be the sweet spot, with either MinP at `0.05` or TopP at `0.9`. DRY/Smoothing etc depending on your preference.
|
| 23 |
+
|
| 24 |
+
## Quantized versions
|
| 25 |
+
|
| 26 |
+
- [iMat GGUFs](https://huggingface.co/Quant-Cartel/Luca-MN-iMat-GGUF)
|