Update README.md
Browse files
README.md
CHANGED
|
@@ -31,6 +31,8 @@ This is a merge of pre-trained language models created using [mergekit](https://
|
|
| 31 |
## Merge Details
|
| 32 |
* This merge is entirely experimental, I've only tested it a few times but it seems to work? Thanks for all the loras jeiku. I keep getting driver crashes training my own :\
|
| 33 |
* Update, It scores well! My highest scoring model so far
|
|
|
|
|
|
|
| 34 |
### Merge Method
|
| 35 |
|
| 36 |
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [ammarali32/multi_verse_model](https://huggingface.co/ammarali32/multi_verse_model) as a base.
|
|
|
|
| 31 |
## Merge Details
|
| 32 |
* This merge is entirely experimental, I've only tested it a few times but it seems to work? Thanks for all the loras jeiku. I keep getting driver crashes training my own :\
|
| 33 |
* Update, It scores well! My highest scoring model so far
|
| 34 |
+
* Self testing results, it can handle non-human characters surprisingly well and does well seperating human actions from non-human actions. I'm happy with it :3
|
| 35 |
+
* Works with alpaca best, Loras' are alpaca. But works with chatml too!
|
| 36 |
### Merge Method
|
| 37 |
|
| 38 |
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [ammarali32/multi_verse_model](https://huggingface.co/ammarali32/multi_verse_model) as a base.
|