metadata

license: mit
datasets:
  - tsac
language:
  - ar

This is a converted version of Instadeep's TunBERT from nemo to safetensors.

Make sure to read the original model licence

architectural changes

original model head

this model head

how to load the model

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("not-lain/TunBERT")
model = AutoModelForSequenceClassification.from_pretrained("not-lain/TunBERT",trust_remote_code=True)

how to use the model

text = "[insert text here]"
inputs = tokenizer(text,return_tensors='pt')
output = model(**inputs)

IMPORTANT :

Make sure to enable trust_remote_code=True
Avoid using the pipeline method