Model serving for NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained NLP model using Hugging Face Transformers.

NLP

from transformers import AutoModelForSequenceClassification
model = AutoModelForSequenceClassification.from_pretrained([1])

Drag options to blanks, or click blank then click option'

Abert-base-uncased

BAutoModel

C"bert-base-uncased"

DSequenceClassifier

Attempts:

3 left

💡 Hint

Common Mistakes

Forgetting to put the model name in quotes.

Using the wrong class name.

The model name must be a string, so it needs to be in quotes.

2fill in blank

medium

Complete the code to tokenize input text for the NLP model.

NLP

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
inputs = tokenizer([1], return_tensors="pt")

Drag options to blanks, or click blank then click option'

Atokenizer

BHello, how are you?

C["Hello", "how", "are", "you"]

D"Hello, how are you?"

Attempts:

3 left

💡 Hint

Common Mistakes

Passing raw text without quotes.

Passing a list of words instead of a string.

The tokenizer expects a string input, so the text must be in quotes.

3fill in blank

hard

Fix the error in the code to get model predictions from tokenized inputs.

NLP

outputs = model([1])
predictions = outputs.logits.argmax(dim=1)

Drag options to blanks, or click blank then click option'

Ainputs['tokens']

Binputs

Cinputs.tensor

Dinputs['input_ids']

Attempts:

3 left

💡 Hint

Common Mistakes

Passing only input_ids instead of the whole inputs dictionary.

Using a wrong key like 'tokens' or 'tensor'.

The model expects the whole inputs dictionary, not just input_ids, to handle attention masks and other inputs.

4fill in blank

hard

Fill both blanks to create a simple Flask API endpoint that serves the NLP model predictions.

NLP

from flask import Flask, request, jsonify
app = Flask(__name__)

@app.route('/predict', methods=['POST'])
def predict():
    data = request.[1].get_json()
    inputs = tokenizer(data['text'], return_tensors='pt')
    outputs = model([2])
    pred = outputs.logits.argmax(dim=1).item()
    return jsonify({'prediction': pred})

Drag options to blanks, or click blank then click option'

Ajson

Binput_ids

Cargs

Ddata

Attempts:

3 left

💡 Hint

Common Mistakes

Using request.args instead of request.json.

Passing the whole inputs dictionary instead of input_ids.

Use request.json to get JSON data and pass inputs['input_ids'] to the model.

5fill in blank

hard

Fill all three blanks to add error handling and run the Flask app for serving the NLP model.

NLP

if __name__ == '__main__':
    try:
        app.run(host=[1], port=[2], debug=[3])
    except Exception as e:
        print(f"Error starting server: {e}")

Drag options to blanks, or click blank then click option'

A"0.0.0.0"

B8080

CTrue

D"localhost"

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'localhost' limits access to local machine only.

Setting debug to False during development.

Use host '0.0.0.0' to allow external access, port 8080, and debug mode True for development.