Homework 1 - Instructions

Step 1: Create embeddings

(Option 1) Run file doc2vec-encoder.py
(Option 2) Run file sentence-transformers.py

Note: Both these files will produce two files called x_train.pkl and x_test.pkl in the root directory.

Step 2: Make predictions

Run file knn.py

Note: This file will produce a prediction file in the root directory.

Step 3 (Optional): Fine tune sentence-transformer model

Run file fine_tune.py
Run file knn.py - but make sure the model is loaded from the fine-tuned model folder in the root directory

Note: This file will produce a file called x_train.pkl and save the model in the root directory.