Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: unlicense
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: unlicense
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- inflatebot/MN-12B-Mag-Mell-R1
|
| 7 |
+
tags:
|
| 8 |
+
- roleplay
|
| 9 |
+
- rp
|
| 10 |
+
- sillytavern
|
| 11 |
+
- gguf
|
| 12 |
+
- llama
|
| 13 |
+
inference: false
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
My GGUF-IQ-ARM-Imatrix quants for [**inflatebot/MN-12B-Mag-Mell-R1**](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1).
|
| 17 |
+
|
| 18 |
+
> Mag Mell R1 was tested with Temp 1.25 and MinP 0.2. This was fairly stable up to 10K, but this might be too "hot". If issues with coherency occur, try increasing MinP or decreasing Temperature.
|
| 19 |
+
|
| 20 |
+
> [!NOTE]
|
| 21 |
+
> Use the **ChatML** prompt format.
|
| 22 |
+
|
| 23 |
+
|