Update README.md
Browse files
README.md
CHANGED
|
@@ -6,8 +6,14 @@ library_name: transformers
|
|
| 6 |
tags:
|
| 7 |
- mergekit
|
| 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).
|
|
@@ -45,4 +51,4 @@ parameters:
|
|
| 45 |
- value: 0.5
|
| 46 |
dtype: bfloat16
|
| 47 |
|
| 48 |
-
```
|
|
|
|
| 6 |
tags:
|
| 7 |
- mergekit
|
| 8 |
- merge
|
| 9 |
+
license: cc-by-nc-4.0
|
| 10 |
---
|
| 11 |
+
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
|
| 12 |
+
|
| 13 |
+
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.
|
| 14 |
+
|
| 15 |
+
I personally use the "Universal Light" preset in silly tavern, with "alpaca" the results can be short but are longer with "alpaca roleplay".
|
| 16 |
+
|
| 17 |
# merge
|
| 18 |
|
| 19 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
| 51 |
- value: 0.5
|
| 52 |
dtype: bfloat16
|
| 53 |
|
| 54 |
+
```
|