Update README.md
Browse files
README.md
CHANGED
|
@@ -22,9 +22,6 @@ v1.1 is just a small fix to not train and save the embeddings layer, since v1.0
|
|
| 22 |
* **Epochs**: 1 epoch training for minimized repetition sickness
|
| 23 |
* **LORA**: 64-rank 128-alpha, resulting in ~2% trainable weights
|
| 24 |
|
| 25 |
-
## Training Loss:
|
| 26 |
-
[Training loss](https://imgur.com/a/1ySVaeH)
|
| 27 |
-
|
| 28 |
## Quantization
|
| 29 |
|
| 30 |
The model is available in quantized formats:
|
|
|
|
| 22 |
* **Epochs**: 1 epoch training for minimized repetition sickness
|
| 23 |
* **LORA**: 64-rank 128-alpha, resulting in ~2% trainable weights
|
| 24 |
|
|
|
|
|
|
|
|
|
|
| 25 |
## Quantization
|
| 26 |
|
| 27 |
The model is available in quantized formats:
|