optimum-cli export openvino --model gpt2 ov_model/

optimum-cli export openvino --model local_model_dir --task text-generation-with-past ov_model/

optimum-cli export openvino --help

usage: optimum-cli export openvino [-h] -m MODEL [--task TASK] [--framework {pt,tf}] [--trust-remote-code] [--weight-format {fp32,fp16,int8,int4}]
                                   [--library {transformers,diffusers,timm,sentence_transformers}] [--cache_dir CACHE_DIR] [--pad-token-id PAD_TOKEN_ID] [--ratio RATIO] [--sym]
                                   [--group-size GROUP_SIZE] [--dataset DATASET] [--all-layers] [--awq] [--scale-estimation] [--sensitivity-metric SENSITIVITY_METRIC] [--num-samples NUM_SAMPLES]
                                   [--disable-stateful] [--disable-convert-tokenizer]
                                   output

optional arguments:
  -h, --help            show this help message and exit

Required arguments:
  --model MODEL         Model ID on huggingface.co or path on disk to load model from.

  output                Path indicating the directory where to store the generated OV model.

Optional arguments:
  --task TASK           The task to export the model for. If not specified, the task will be auto-inferred based on the model. Available tasks depend on the model, but are among: ['image-segmentation',
                        'feature-extraction', 'mask-generation', 'audio-classification', 'conversational', 'stable-diffusion-xl', 'question-answering', 'sentence-similarity', 'text2text-generation',
                        'masked-im', 'automatic-speech-recognition', 'fill-mask', 'image-to-text', 'text-generation', 'zero-shot-object-detection', 'multiple-choice', 'object-detection', 'stable-
                        diffusion', 'audio-xvector', 'text-to-audio', 'zero-shot-image-classification', 'token-classification', 'image-classification', 'depth-estimation', 'image-to-image', 'audio-
                        frame-classification', 'semantic-segmentation', 'text-classification']. For decoder models, use `xxx-with-past` to export the model using past key values in the decoder.
  --framework {pt,tf}   The framework to use for the export. If not provided, will attempt to use the local checkpoints original framework or what is available in the environment.
  --trust-remote-code   Allows to use custom code for the modeling hosted in the model repository. This option should only be set for repositories you trust and in which you have read the code, as it
                        will execute on your local machine arbitrary code present in the model repository.
  --weight-format {fp32,fp16,int8,int4}
                        The weight format of the exported model.
  --library {transformers,diffusers,timm,sentence_transformers}
                        The library used to load the model before export. If not provided, will attempt to infer the local checkpoints library.
  --cache_dir CACHE_DIR
                        The path to a directory in which the downloaded model should be cached if the standard cache should not be used.
  --pad-token-id PAD_TOKEN_ID
                        This is needed by some models, for some tasks. If not provided, will attempt to use the tokenizer to guess it.
  --ratio RATIO         A parameter used when applying 4-bit quantization to control the ratio between 4-bit and 8-bit quantization. If set to 0.8, 80% of the layers will be quantized to int4 while
                        20% will be quantized to int8. This helps to achieve better accuracy at the sacrifice of the model size and inference latency. Default value is 0.8.
  --sym                 Whether to apply symmetric quantization
  --group-size GROUP_SIZE
                        The group size to use for int4 quantization. Recommended value is 128 and -1 will results in per-column quantization.
  --dataset DATASET     The dataset used for data-aware compression or quantization with NNCF. You can use the one from the list ['wikitext2','c4','c4-new'] for language models or
                        ['conceptual_captions','laion/220k-GPT4Vision-captions-from-LIVIS','laion/filtered-wit'] for diffusion models.
  --all-layers          Whether embeddings and last MatMul layers should be compressed to INT4. If not provided an weight compression is applied, they are compressed to INT8.
  --awq                 Whether to apply AWQ algorithm. AWQ improves generation quality of INT4-compressed LLMs, but requires additional time for tuning weights on a calibration dataset. To run AWQ,
                        please also provide a dataset argument. Note: it is possible that there will be no matching patterns in the model to apply AWQ, in such case it will be skipped.
  --scale-estimation    Indicates whether to apply a scale estimation algorithm that minimizes the L2 error between the original and compressed layers. Providing a dataset is required to run scale
                        estimation. Please note, that applying scale estimation takes additional memory and time.
  --sensitivity-metric SENSITIVITY_METRIC
                        The sensitivity metric for assigning quantization precision to layers. Can be one of the following: ['weight_quantization_error', 'hessian_input_activation',
                        'mean_activation_variance', 'max_activation_variance', 'mean_activation_magnitude'].
  --num-samples NUM_SAMPLES
                        The maximum number of samples to take from the dataset for quantization.
  --disable-stateful    Disable stateful converted models, stateless models will be generated instead. Stateful models are produced by default when this key is not used. In stateful models all kv-cache
                        inputs and outputs are hidden in the model and are not exposed as model inputs and outputs. If --disable-stateful option is used, it may result in sub-optimal inference
                        performance. Use it when you intentionally want to use a stateless model, for example, to be compatible with existing OpenVINO native inference code that expects kv-cache inputs
                        and outputs in the model.
  --disable-convert-tokenizer
                        Do not add converted tokenizer and detokenizer OpenVINO models.

optimum-cli export openvino --model gpt2 --weight-format int8 ov_model/

- from transformers import AutoModelForCausalLM
+ from optimum.intel import OVModelForCausalLM
  from transformers import AutoTokenizer

  model_id = "gpt2"
- model = AutoModelForCausalLM.from_pretrained(model_id)
+ model = OVModelForCausalLM.from_pretrained(model_id, export=True)
  tokenizer = AutoTokenizer.from_pretrained(model_id)

  save_directory = "ov_model"
  model.save_pretrained(save_directory)
  tokenizer.save_pretrained(save_directory)

from transformers import AutoModelForCausalLM
from optimum.exporters.openvino import export_from_model

model = AutoModelForCausalLM.from_pretrained("gpt2")
export_from_model(model, output="ov_model", task="text-generation-with-past")