Downloads · 30 days
19
6% of all-time downloads
z-uo/bert-italian-ner-onnx-quantized-avx512
bert-italian-ner-onnx-quantized-avx512 is a token classification model from z-uo. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
This model is the onnx version of nickprock/bert-italian-finetuned-ner.
Downloads · 30 days
19
6% of all-time downloads
All-time downloads
339
Public
Repo size
110 MB
Likes
1
Public
Click a slice to open those files.
.onnx110 MB · 99%
From the Hugging Face model README
This model is the onnx version of nickprock/bert-italian-finetuned-ner.
To use you need to intall following libraries:
pip install optimum onnxruntime onnx
And run with the following script:
import time
from transformers import AutoTokenizer, pipeline
from optimum.onnxruntime import ORTModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("z-uo/bert-italian-ner-onnx-quantized-avx512")
model = ORTModelForTokenClassification.from_pretrained("z-uo/bert-italian-ner-onnx-quantized-avx512")
nerpipeline = pipeline('ner', model=model, tokenizer=tokenizer)
text = "La sede storica della Olivetti è ad Ivrea"
output = nerpipeline(text)