from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("tunis-ai/TunBERT")
model = AutoModelForSequenceClassification.from_pretrained("tunis-ai/TunBERT",trust_remote_code=True)

how to use the model

python

text = "[insert text here]"
inputs = tokenizer(text,return_tensors='pt')
output = model.process(**inputs) # -> List["positive" or "negative"]

or you can use the normal forward method (currently compatible with the Trainer class)

python

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

or you can use the pipeline :

⚠️currently broken try an older version of transformers until i raise this, in the mean time use the model.process method mentioned above

python

from transformers import pipeline

pipe = pipeline(model="tunis-ai/TunBERT",tokenizer = "tunis-ai/TunBERT",trust_remote_code=True)
pipe("text")