Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,16 @@ tags:
|
|
| 8 |
- merge
|
| 9 |
|
| 10 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
# merge
|
| 12 |
|
| 13 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
| 8 |
- merge
|
| 9 |
|
| 10 |
---
|
| 11 |
+
GGUFs' for https://huggingface.co/saishf/Fimbulvetr-Kuro-Lotus-10.7B
|
| 12 |
+
|
| 13 |
+
This model is a merge of my personal favourite models, i couldn't decide between them so why not have both? Without MOE cause gpu poor :3
|
| 14 |
+
|
| 15 |
+
With my own tests it gives kuro-lotus like results without the requirement for a highly detailed character card and stays coherent when roping up to 8K context.
|
| 16 |
+
|
| 17 |
+
I personally use the "Universal Light" preset in silly tavern, with "alpaca" the results can be short but are longer with "alpaca roleplay".
|
| 18 |
+
|
| 19 |
+
"Universal Light" preset can be extremely creative but sometimes likes to act for user with some cards, for those i like just the "default" but any preset seems to work!
|
| 20 |
+
|
| 21 |
# merge
|
| 22 |
|
| 23 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|