Downloads · 30 days
14
5% of all-time downloads
convbert-base-turkish-cased-ner-quantized
akdeniz27/convbert-base-turkish-cased-ner-quantized
convbert-base-turkish-cased-ner-quantized is a token classification model from akdeniz27. 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 dynamically quantized version of the model (https://akdeniz27/convbert-base-turkish-cased-ner)
All-time downloads
277
Public
Repo size
193 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx193 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- convbert
- Access
- Public
- Created
- Nov 28, 2022
- Updated
- Dec 23, 2022
- SHA
- ef20d8aa
Model card
From the Hugging Face model README
Turkish Named Entity Recognition (NER) Quantized Model
This model is the dynamically quantized version of the model (https://akdeniz27/convbert-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_onnx = ORTModelForTokenClassification.from_pretrained("akdeniz27/convbert-base-turkish-cased-ner-quantized", file_name="model_quantized.onnx")
tokenizer = AutoTokenizer.from_pretrained("akdeniz27/convbert-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.
- Task
- Token Classification
- Library
- transformers
- Type
- convbert
- License
- mit
- Languages
- tr
- Created
- Nov 28, 2022
- Updated
- Dec 23, 2022