akdeniz27/bert-base-turkish-cased-ner-quantized

By akdeniz27 · ↓ 13 · ♥ 1 · Updated 2022-12-23

What's in this repo

This page lists the files in akdeniz27/bert-base-turkish-cased-ner-quantized, including model_quantized.onnx.

1 ONNX models (.onnx files)
10 files, including 5 .json, 1 .md, 1 .onnx, 1 .model, 1 .txt
Last updated 2022-12-23

ONNX files

File	Size	Download
model_quantized.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Turkish Named Entity Recognition (NER) Quantized Model

This model is the dynamically quantized version of the model (https://akdeniz27/bert-base-turkish-cased-ner)

How to use:

# First install "optimum[onnxruntime]":
!pip install "optimum[onnxruntime]"

# and import "ORTModelForTokenClassification":
from transformers import AutoTokenizer, pipeline
from optimum.onnxruntime import ORTModelForTokenClassification

model = ORTModelForTokenClassification.from_pretrained("akdeniz27/bert-base-turkish-cased-ner-quantized", file_name="model_quantized.onnx")
tokenizer = AutoTokenizer.from_pretrained("akdeniz27/bert-base-turkish-cased-ner-quantized")
ner = pipeline('ner', model=model, tokenizer=tokenizer, aggregation_strategy="first")
ner("your text here")

Pls refer (https://github.com/akdeniz27/dynamic_quantization) for details of quantization.

Model info

token-classification transformers

transformers onnx bert token-classification tr license:mit endpoints_compatible region:us

↓ 13 ♥ 1

Created: 2022-11-20

Updated: 2022-12-23

View on Hugging Face

Files (10)

.gitattributes

README.md

config.json

model_quantized.onnx ONNX

ort_config.json

sentencepiece.bpe.model

special_tokens_map.json

tokenizer.json

tokenizer_config.json

vocab.txt

Related models

More token-classification models

Browse all token-classification models