Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ Original model: https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
|
|
| 16 |
|
| 17 |
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
|
| 18 |
|
|
|
|
|
|
|
| 19 |
## Prompt format
|
| 20 |
|
| 21 |
```
|
|
|
|
| 16 |
|
| 17 |
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
|
| 18 |
|
| 19 |
+
Experimental quants are made with `--output-tensor-type f16 --token-embedding-type f16` per [ZeroWw](https://huggingface.co/ZeroWw)'s suggestion, please provide any feedback on quality differences you spot.
|
| 20 |
+
|
| 21 |
## Prompt format
|
| 22 |
|
| 23 |
```
|