Commit
•
5492af4
1
Parent(s):
ac422b2
Updating README
Browse files
README.md
CHANGED
|
@@ -21,7 +21,8 @@ This model has been quantized in INT4, group-size 128, and optimized for inferen
|
|
| 21 |
## 🚨 Reproducibility
|
| 22 |
This model has been quantized using Intel [auto-round](https://github.com/intel/auto-round), based on [SignRound technique](https://arxiv.org/pdf/2309.05516v4).
|
| 23 |
|
| 24 |
-
```
|
|
|
|
| 25 |
--model_name ./models/sapienzanlp_modello-italia-9b \
|
| 26 |
--device 0 \
|
| 27 |
--group_size 128 \
|
|
|
|
| 21 |
## 🚨 Reproducibility
|
| 22 |
This model has been quantized using Intel [auto-round](https://github.com/intel/auto-round), based on [SignRound technique](https://arxiv.org/pdf/2309.05516v4).
|
| 23 |
|
| 24 |
+
```
|
| 25 |
+
python3 ./examples/language-modeling/main.py \
|
| 26 |
--model_name ./models/sapienzanlp_modello-italia-9b \
|
| 27 |
--device 0 \
|
| 28 |
--group_size 128 \
|