Update README.md
Browse files
README.md
CHANGED
|
@@ -28,6 +28,8 @@ Original model: https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
|
|
| 28 |
|
| 29 |
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
|
| 30 |
|
|
|
|
|
|
|
| 31 |
## Prompt format
|
| 32 |
|
| 33 |
```
|
|
|
|
| 28 |
|
| 29 |
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
|
| 30 |
|
| 31 |
+
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.
|
| 32 |
+
|
| 33 |
## Prompt format
|
| 34 |
|
| 35 |
```
|