Add OpenVINO pipelines

[echarlaix]

Add pipelines able to load a model and convert it to the openvino format if needed

from optimum.intel.pipelines import pipeline

# Load openvino model
ov_pipe = pipeline("text-generation", "helenai/gpt2-ov", accelerator="openvino")
# Load pytorch model and convert it to openvino before inference
pipe = pipeline("text-generation", "gpt2", accelerator="openvino")

@helena-intel @eaidova

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.