Update README.md
Browse files
README.md
CHANGED
|
@@ -19,8 +19,6 @@ This is an INT8 PyTorch model quantized with [huggingface/optimum-intel](https:
|
|
| 19 |
|
| 20 |
The original fp32 model comes from the fine-tuned model [adasnew/t5-small-xsum](https://huggingface.co/adasnew/t5-small-xsum).
|
| 21 |
|
| 22 |
-
The calibration dataloader is the train dataloader. The default calibration sampling size 100 isn't divisible exactly by batch size 8, so the real sampling size is 104.
|
| 23 |
-
|
| 24 |
The linear modules **lm.head**, fall back to fp32 for less than 1% relative accuracy loss.
|
| 25 |
|
| 26 |
### Evaluation result
|
|
|
|
| 19 |
|
| 20 |
The original fp32 model comes from the fine-tuned model [adasnew/t5-small-xsum](https://huggingface.co/adasnew/t5-small-xsum).
|
| 21 |
|
|
|
|
|
|
|
| 22 |
The linear modules **lm.head**, fall back to fp32 for less than 1% relative accuracy loss.
|
| 23 |
|
| 24 |
### Evaluation result
|