How to Deploy a Hugging Face Transformers Model for Inference Using KServe (without KServe 0.13v)?

Question

I'm working on deploying a pre-trained Hugging Face Transformer models for inference using KServe, but my Kubernetes environment does not support KServe 0.13v. I've researched the topic and found various guides on deploying models with KServe, but most of them are tailored to version 0.13v.

Questions:

Can you provide detailed steps or adjustments needed to deploy the model with KServe (version lower than 0.13v)?

Are there any specific considerations or configurations required for older versions of KServe?

I have tried the following:

Preparing the model and tokenizer using the Hugging Face Transformers library.

Creating a Dockerfile to package the model and necessary dependencies.

Writing an inference script to load the model and handle prediction requests.

Building and pushing the Docker image to a container registry.

Defining the KServe InferenceService YAML configuration for deployment.