ONNX-converted models
Collection
Models converted to ONNX for faster CPU inference on LLM Guard.
•
27 items
•
Updated
This model is a conversion of dbmdz/bert-large-cased-finetuned-conll03-english to ONNX format using the 🤗 Optimum library.
dbmdz/bert-large-cased-finetuned-conll03-english
is designed for named-entity recognition (NER), capable of finding person, organization, and other entities in the text.
Loading the model requires the 🤗 Optimum library installed.
from optimum.onnxruntime import ORTModelForTokenClassification
from transformers import AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("laiyer/bert-large-cased-finetuned-conll03-english-onnx")
model = ORTModelForTokenClassification.from_pretrained("laiyer/bert-large-cased-finetuned-conll03-english-onnx")
ner = pipeline(
task="ner",
model=model,
tokenizer=tokenizer,
)
ner_output = ner("My name is John Doe.")
print(ner_output)
Join our Slack to give us feedback, connect with the maintainers and fellow users, ask questions, or engage in discussions about LLM security!