Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- it
|
4 |
+
license: mit
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
widget:
|
8 |
+
- text: 'Ciao, sono Giacomo. Vivo a Milano e lavoro da Armani. '
|
9 |
+
example_title: Example 1
|
10 |
+
- text: 'Domenica andrò allo stadio con Giovanna a guardare la Fiorentina. '
|
11 |
+
example_title: Example 2
|
12 |
+
base_model: nickprock/bert-italian-finetuned-ner
|
13 |
+
---
|
14 |
+
# Bert Italian NER ONNX avx512
|
15 |
+
This model is the onnx version of nickprock/bert-italian-finetuned-ner.
|
16 |
+
|
17 |
+
|
18 |
+
To use you need to intall following libraries:
|
19 |
+
|
20 |
+
```bash
|
21 |
+
pip install optimum onnxruntime onnx
|
22 |
+
```
|
23 |
+
|
24 |
+
And run with the following script:
|
25 |
+
|
26 |
+
```python
|
27 |
+
import time
|
28 |
+
from transformers import AutoTokenizer, pipeline
|
29 |
+
from optimum.onnxruntime import ORTModelForTokenClassification
|
30 |
+
|
31 |
+
tokenizer = AutoTokenizer.from_pretrained("z-uo/bert-italian-ner-onnx-quantized-avx512")
|
32 |
+
model = ORTModelForTokenClassification.from_pretrained("z-uo/bert-italian-ner-onnx-quantized-avx512")
|
33 |
+
nerpipeline = pipeline('ner', model=model, tokenizer=tokenizer)
|
34 |
+
|
35 |
+
text = "La sede storica della Olivetti è ad Ivrea"
|
36 |
+
output = nerpipeline(text)
|
37 |
+
```
|