HuggingFace-Model-Serving | easy tutorial to serve HuggingFace sentiment analysis model

We will require following components available for serving. It is a good idea to create and activate a python virtual environment with name of your choice before installing python dependencies. We may want to call it "torchserve" as an environment. -Transformers As we will be serving Transformer model, we will require to install Transformers using following command.
JDK 11 You may need to sign up to oracle to download archived version of JDK to be able to download and install TorchServe uses JDK for HTTP server support.
pytorch Install torchserve and related components using below command
We will first download the transformer model locally, then archieve it to model archieve file (.mar) and serve it using Torch Serve. -Step 2 - Clone or download and extract serve repo to your machine from Torch Serve repo. we will require a couple of files from this repo. this will give you "serve-master" directory with all the artificates. This will create a new folder Transformer_model under current directory & download transformar model mentioned in setup_config.json and and all required artifacts. If everything goes well, you should see a message like below in the terminal log Transformer model from path loaded successfully. This confirms that you are now serving pretrained Huggingface sentiment analysis model as a REST API.
Step 1 - Lets create and change directory to a local folder named "sentiment_deployment".
Step 3 - copy following files from serve-master folder of serve repo to sentiment_deployment folder. serve-master/examples/Huggingface_Transformers/setup_config.json serve-master/examples/Huggingface_Transformers/Download_Transformer_models.py serve-master/examples/Huggingface_Transformers/Transformer_handler_generalized.py serve-master/examples/Huggingface_Transformers/Seq_classification_artifacts/index_to_name.json
Step 4 - Edit setup_config.json to have following content.
Step 5 - Edit index_to_name.json to have following content.
Step 6 - Let's now download Transformer model using following command
Step 6 - Let's create Model Archieve (.mar) using following command. Please ensure that you have all the files at correct places. If you have follwed the steps correctly then these files should be in correct places.
Step 7 - Create a directory named model_store under current directory and move your new archieved model file to this folder
Step 8 - This is the final step in serving the model. We will run torchserve as below