metadata

language:
  - en
tags:
  - openvino

echarlaix/bert-large-uncased-whole-word-masking-finetuned-sst-2

This is the echarlaix/bert-large-uncased-whole-word-masking-finetuned-sst-2 model converted to OpenVINO, for accelerated inference.

An example of how to do inference on this model:

# pip install optimum[openvino]
from optimum.intel import OVModelForSequenceClassification
from transformers import AutoTokenizer, pipeline

# model_id should be set to either a local directory or a model available on the HuggingFace hub.
model_id = "helenai/echarlaix-bert-large-uncased-whole-word-masking-finetuned-sst-2-ov"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForSequenceClassification.from_pretrained(model_id)
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
result = pipe("hello world")
print(result)