from datasets import load_dataset, load_metric
from transformers import AutoConfig,AutoModelForSequenceClassification,AutoTokenizer

raw_datasets = load_dataset("glue", "sst2")
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
raw_datasets = raw_datasets.map(lambda e: tokenizer(e['sentence'], truncation=True, padding='max_length', max_length=128), batched=True)

from intel_extension_for_transformers.optimization import QuantizationConfig, metrics, objectives
from intel_extension_for_transformers.optimization.trainer import NLPTrainer

config = AutoConfig.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english",num_labels=2)
model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english",config=config)
model.config.label2id = {0: 0, 1: 1}
model.config.id2label = {0: 'NEGATIVE', 1: 'POSITIVE'}
# Replace transformers.Trainer with NLPTrainer
# trainer = transformers.Trainer(...)
trainer = NLPTrainer(model=model, 
    train_dataset=raw_datasets["train"], 
    eval_dataset=raw_datasets["validation"],
    tokenizer=tokenizer
)
q_config = QuantizationConfig(metrics=[metrics.Metric(name="eval_loss", greater_is_better=False)])
model = trainer.quantize(quant_config=q_config)

input = tokenizer("I like Intel Extension for Transformers", return_tensors="pt")
output = model(**input).logits.argmax().item()