from evaluate import evaluator
from datasets import load_dataset
 
eval = evaluator("text-classification")
eval_dataset = load_dataset("banking77", split="test")
 
results = eval.compute(
    model_or_pipeline=q8_clf,
    data=eval_dataset,
    metric="accuracy",
    input_column="text",
    label_column="label",
    label_mapping=model.config.label2id,
    strategy="simple",
)
print(results)