from optimum.intel import OVModelForCausalLM

model_id = "helenai/gpt2-ov"
model = OVModelForCausalLM.from_pretrained(model_id, load_in_8bit=True)

# Saves the int8 model that will be x4 smaller than its fp32 counterpart
model.save_pretrained(saving_directory)

from optimum.intel import OVModelForCausalLM, OVWeightQuantizationConfig

quantization_config = OVWeightQuantizationConfig(bits=4)
model = OVModelForCausalLM.from_pretrained(model_id, quantization_config=quantization_config)

quantization_config = OVWeightQuantizationConfig(bits=4, sym=False, ratio=0.8, dataset="wikitext2")

quantization_config = OVWeightQuantizationConfig(bits=4, sym=False, ratio=0.8, quant_method="awq", scale_estimation=True, dataset="wikitext2")

from transformers import AutoTokenizer
from optimum.intel import OVQuantizer, OVModelForSequenceClassification, OVConfig, OVQuantizationConfig

model_id = "distilbert-base-uncased-finetuned-sst-2-english"
model = OVModelForSequenceClassification.from_pretrained(model_id, export=True)
tokenizer = AutoTokenizer.from_pretrained(model_id)
# The directory where the quantized model will be saved
save_dir = "ptq_model"

quantizer = OVQuantizer.from_pretrained(model)

# Apply static quantization and export the resulting quantized model to OpenVINO IR format
ov_config = OVConfig(quantization_config=OVQuantizationConfig())
quantizer.quantize(ov_config=ov_config, calibration_dataset=calibration_dataset, save_directory=save_dir)
# Save the tokenizer
tokenizer.save_pretrained(save_dir)

from functools import partial

def preprocess_function(examples, tokenizer):
    return tokenizer(examples["sentence"], padding="max_length", max_length=128, truncation=True)

# Create the calibration dataset used to perform static quantization
calibration_dataset = quantizer.get_calibration_dataset(
    "glue",
    dataset_config_name="sst2",
    preprocess_function=partial(preprocess_function, tokenizer=tokenizer),
    num_samples=300,
    dataset_split="train",
)

from optimum.intel import OVStableDiffusionPipeline, OVWeightQuantizationConfig

model = OVStableDiffusionPipeline.from_pretrained(
    model_id,
    export=True,
    quantization_config=OVWeightQuantizationConfig(bits=8, dataset="conceptual_captions"),
)

  import evaluate
  import numpy as np
  from transformers import (
      AutoModelForSequenceClassification,
      AutoTokenizer,
      TrainingArguments,
      default_data_collator,
  )
  from datasets import load_dataset
- from transformers import Trainer
+ from optimum.intel import OVConfig, OVTrainer, OVModelForSequenceClassification

  model_id = "distilbert-base-uncased-finetuned-sst-2-english"
  model = AutoModelForSequenceClassification.from_pretrained(model_id)
  tokenizer = AutoTokenizer.from_pretrained(model_id)
  # The directory where the quantized model will be saved
  save_dir = "qat_model"
  dataset = load_dataset("glue", "sst2")
  dataset = dataset.map(
      lambda examples: tokenizer(examples["sentence"], padding=True), batched=True
  )
  metric = evaluate.load("glue", "sst2")

  def compute_metrics(eval_preds):
      preds = np.argmax(eval_preds.predictions, axis=1)
      return metric.compute(predictions=preds, references=eval_preds.label_ids)

  # Load the default quantization configuration detailing the quantization we wish to apply
+ ov_config = OVConfig()

- trainer = Trainer(
+ trainer = OVTrainer(
      model=model,
      args=TrainingArguments(save_dir, num_train_epochs=1.0, do_train=True, do_eval=True),
      train_dataset=dataset["train"].select(range(300)),
      eval_dataset=dataset["validation"],
      compute_metrics=compute_metrics,
      tokenizer=tokenizer,
      data_collator=default_data_collator,
+     ov_config=ov_config,
+     task="text-classification",
)

  # Train the model while applying quantization
  train_result = trainer.train()
  metrics = trainer.evaluate()
  # Export the quantized model to OpenVINO IR format and save it
  trainer.save_model()

  # Load the resulting quantized model
- model = AutoModelForSequenceClassification.from_pretrained(save_dir)
+ model = OVModelForSequenceClassification.from_pretrained(save_dir)

compression_config = [
    {
        "compression":
        {
        "algorithm":  "movement_sparsity",
        "params": {
            "warmup_start_epoch":  1,
            "warmup_end_epoch":    4,
            "importance_regularization_factor":  0.01,
            "enable_structured_masking":  True
        },
        "sparse_structure_by_scopes": [
            {"mode":  "block",   "sparse_factors": [32, 32], "target_scopes": "{re}.*BertAttention.*"},
            {"mode":  "per_dim", "axis":  0,                 "target_scopes": "{re}.*BertIntermediate.*"},
            {"mode":  "per_dim", "axis":  1,                 "target_scopes": "{re}.*BertOutput.*"},
        ],
        "ignored_scopes": ["{re}.*NNCFEmbedding", "{re}.*pooler.*", "{re}.*LayerNorm.*"]
        }
    },
    {
        "algorithm": "quantization",
        "weights": {"mode": "symmetric"}
        "activations": { "mode": "symmetric"},
    }
]

- from transformers import Trainer, TrainingArguments
+ from optimum.intel import OVConfig, OVTrainer, OVTrainingArguments

  # Load teacher model
+ teacher_model = AutoModelForSequenceClassification.from_pretrained(teacher_model_or_path)

- ov_config = OVConfig()
+ ov_config = OVConfig(compression=compression_config)

  trainer = OVTrainer(
      model=model,
+     teacher_model=teacher_model,
-     args=TrainingArguments(save_dir, num_train_epochs=1.0, do_train=True, do_eval=True),
+     args=OVTrainingArguments(save_dir, num_train_epochs=1.0, do_train=True, do_eval=True, distillation_temperature=3, distillation_weight=0.9),
      train_dataset=dataset["train"].select(range(300)),
      eval_dataset=dataset["validation"],
      compute_metrics=compute_metrics,
      tokenizer=tokenizer,
      data_collator=default_data_collator,
+     ov_config=ov_config,
      task="text-classification",
  )

  # Train the model like usual, internally the training is applied with pruning, quantization and distillation
  train_result = trainer.train()
  metrics = trainer.evaluate()
  # Export the quantized model to OpenVINO IR format and save it
  trainer.save_model()

from transformers import pipeline
from optimum.intel import OVModelForSequenceClassification

model_id = "helenai/distilbert-base-uncased-finetuned-sst-2-english-ov-int8"
ov_model = OVModelForSequenceClassification.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
cls_pipe = pipeline("text-classification", model=ov_model, tokenizer=tokenizer)
text = "He's a dreadful magician."
outputs = cls_pipe(text)

[{'label': 'NEGATIVE', 'score': 0.9840195178985596}]