added onboarding instructions

Author: npatta01

.gitignore

@@ -9,3 +9,4 @@ __pycache__
 *.zip
 notebooks/trainer_*/ 
 notebooks/wandb/
+.venv

README.md

@@ -6,34 +6,44 @@
 
 This repo contains notebooks for Pytorch Serving Workshop.
 
+Note: We **do not** need a GPU runtime
 
-To get started, run the below notebook that will setup everything in collab. 
+## Setup 
 
-**Colab** starter notebook:    [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/npatta01/pytorch-serving-workshop/blob/main/colab_starter.ipynb)
+1) Run the below notebook that will setup everything in collab. 
 
+    **Colab** starter notebook:    [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/npatta01/pytorch-serving-workshop/blob/main/colab_starter.ipynb)
+
+2) Navigate to the ngrok proxy url
+![](assets/setup_01.png)
+
+    We use ngrok to acces the underlying collab runtime
+
+3) Navigate to working directory in VSCode
+![](assets/setup_02.png)
 
 ## Contents
 
 There are five notebooks.
 
-a. 00_prepare_dataset.ipynb
+a. `00_prepare_dataset.ipynb`
 
 Notebook that prepares the e-comeerce dataset and saves it.
 
-b. 01_train.ipynb
+b. `01_train.ipynb`
 
 Trains a DistilBert model
 
-c. 02_inference_review.ipynb
+c. `02_inference_review.ipynb`
 
 Notebook that shows how to use the HuggingFace ecosystem. Also shows how to use the trained model from previous notebook.
 
-d. 03_optimizing_model.ipynb
+d. `03_optimizing_model.ipynb`
 
 Notebook that shows impact of Quantization and TorschScript
 
 
-e. 04_packaging.ipynb
+e. `04_packaging.ipynb`
 
 Notebook that shows how to use TorchServe to serve models