Transformer architecture in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a Transformer encoder layer using PyTorch.

NLP

import torch.nn as nn
encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=[1])

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

A16

B4

C8

D32

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing a number of heads that does not divide the model dimension evenly.

The number of attention heads (nhead) is commonly set to 8 in Transformer models for balanced performance.

2fill in blank

medium

Complete the code to apply positional encoding to the input embeddings.

NLP

pos_encoded = embeddings + [1]

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

Ann.Embedding(num_positions, embedding_dim)

Bpositional_encoding

Cnn.Linear(embedding_dim, embedding_dim)

Dnn.LayerNorm(embedding_dim)

Attempts:

3 left

💡 Hint

Common Mistakes

Using a layer like nn.Embedding or nn.Linear instead of a positional encoding tensor.

Positional encoding is added to embeddings to give the model information about token positions.

3fill in blank

hard

Fix the error in the multi-head attention call by filling the correct argument.

NLP

output, weights = multihead_attn(query, key, [1])

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

Avalue

Bmask

Ckey_padding_mask

Dattn_mask

Attempts:

3 left

💡 Hint

Common Mistakes

Passing mask or key_padding_mask as the third positional argument instead of value.

The third argument to multihead_attn is the value tensor, which is used along with query and key.

4fill in blank

hard

Fill both blanks to complete the Transformer decoder layer initialization.

NLP

decoder_layer = nn.TransformerDecoderLayer(d_model=[1], nhead=[2])

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

A512

B256

C8

D4

Attempts:

3 left

💡 Hint

Common Mistakes

Mismatching d_model and nhead values that don't align with embedding size.

The decoder layer uses d_model=512 and nhead=8 to match common Transformer settings.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps each token to its embedding size if the size is greater than 300.

NLP

embedding_sizes = {token: [1] for token, size in token_sizes.items() if size [2] 300 and size == [3]

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

Asize

B>

C512

Dtoken

Attempts:

3 left

💡 Hint

Common Mistakes

Using token instead of size as dictionary value or wrong comparison operators.

This comprehension selects tokens with embedding size greater than 300 and exactly 512, mapping token to size.

Practice

1. What is the main purpose of the self-attention mechanism in a Transformer model?

easy

A. To increase the number of layers in the model

B. To reduce the size of the input data

C. To convert words into numbers

D. To let the model focus on different words in the sentence at the same time

Solution

1. Step 1: Understand self-attention role

   Self-attention helps the model look at all words together and decide which words are important for each word.

2. Step 2: Match purpose with options

   To let the model focus on different words in the sentence at the same time correctly describes this as focusing on different words simultaneously, unlike other options which describe unrelated tasks.

3. Final Answer:

   To let the model focus on different words in the sentence at the same time -> Option D

4. Quick Check:

   Self-attention = focus on words together [OK]

Hint: Self-attention means focusing on all words at once [OK]

Common Mistakes:

• Thinking self-attention reduces input size
• Confusing self-attention with embedding
• Assuming it increases model layers

2. Which of the following is the correct way to describe the Transformer architecture components?

easy

A. It has encoder and decoder parts

B. It has only an encoder part

C. It uses only convolutional layers

D. It uses recurrent neural networks

Solution

1. Step 1: Recall Transformer structure

   Transformers have two main parts: encoder to process input and decoder to generate output.

2. Step 2: Compare options with structure

   It has encoder and decoder parts correctly states the presence of both encoder and decoder; others mention incorrect or unrelated components.

3. Final Answer:

   It has encoder and decoder parts -> Option A

4. Quick Check:

   Transformer = encoder + decoder [OK]

Hint: Remember: Transformer = encoder + decoder [OK]

Common Mistakes:

• Thinking Transformer has only encoder
• Confusing Transformer with CNN or RNN
• Ignoring decoder role

3. Consider this simplified Transformer encoder code snippet in Python using PyTorch:

import torch
from torch import nn

class SimpleEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.attention = nn.MultiheadAttention(embed_dim=4, num_heads=2)
    def forward(self, x):
        attn_output, _ = self.attention(x, x, x)
        return attn_output

x = torch.rand(5, 3, 4)  # sequence length=5, batch=3, embed=4
model = SimpleEncoder()
output = model(x)
print(output.shape)

What will be the printed output shape?

medium

A. torch.Size([3, 5, 4])

B. torch.Size([5, 3, 4])

C. torch.Size([5, 4, 3])

D. torch.Size([3, 4, 5])

Solution

1. Step 1: Understand input shape and MultiheadAttention

   Input shape is (sequence length=5, batch=3, embedding=4). PyTorch MultiheadAttention expects (seq_len, batch, embed).

2. Step 2: Output shape matches input shape

   MultiheadAttention returns output with the same shape as input: (5, 3, 4).

3. Final Answer:

   torch.Size([5, 3, 4]) -> Option B

4. Quick Check:

   Output shape = input shape for MultiheadAttention [OK]

Hint: MultiheadAttention output shape matches input shape [OK]

Common Mistakes:

• Mixing batch and sequence dimensions
• Assuming output shape changes embedding size
• Confusing PyTorch input format

4. You have this Transformer decoder code snippet that throws an error:

import torch
from torch import nn

class SimpleDecoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.attention = nn.MultiheadAttention(embed_dim=8, num_heads=4)
    def forward(self, tgt, memory):
        attn_output, _ = self.attention(tgt, memory, memory)
        return attn_output

tgt = torch.rand(10, 2, 8)  # target seq len=10, batch=2, embed=8
memory = torch.rand(5, 3, 8)  # memory seq len=5, batch=3, embed=8
model = SimpleDecoder()
output = model(tgt, memory)
print(output.shape)

What is the likely cause of the error?

medium

A. Sequence length mismatch between tgt and memory

B. Mismatch in embedding dimensions between tgt and memory

C. Batch size mismatch between tgt and memory

D. Number of attention heads is too high

Solution

1. Step 1: Check shapes of tgt and memory

   tgt=(10,2,8), memory=(5,3,8). Both have embedding size 8, sequence lengths differ (10 vs 5, allowed), but batch sizes differ (2 vs 3).

2. Step 2: Identify batch size mismatch

   Batch size mismatch between tgt (batch=2) and memory (batch=3) causes the RuntimeError in MultiheadAttention.

3. Step 3: Re-examine options carefully

   Embedding sizes match, sequence length mismatch is allowed, number of heads is valid. Batch size mismatch is most common error in such cases.

4. Final Answer:

   Batch size mismatch between tgt and memory -> Option C

5. Quick Check:

   Batch sizes must match for attention [OK]

Hint: Check batch sizes first when attention errors occur [OK]

Common Mistakes:

• Assuming sequence length must match
• Blaming embedding size mismatch incorrectly
• Thinking number of heads causes shape errors

5. You want to build a Transformer model for text summarization. Which combination of components is best suited for this task?

hard

A. Encoder-decoder, because summarization needs understanding input and generating output

B. Decoder only, because summarization is text generation

C. Neither encoder nor decoder, use RNN instead

D. Encoder only, because summarization needs understanding input only

Solution

1. Step 1: Understand summarization task

   Summarization requires reading input text (encoding) and producing a shorter text (decoding).

2. Step 2: Match task with Transformer parts

   Encoder-decoder architecture fits best as encoder understands input and decoder generates summary output.

3. Final Answer:

   Encoder-decoder, because summarization needs understanding input and generating output -> Option A

4. Quick Check:

   Summarization = encoder + decoder [OK]

Hint: Summarization needs both understanding and generating text [OK]

Common Mistakes:

• Choosing encoder only for generation tasks
• Choosing decoder only ignoring input understanding
• Ignoring Transformer benefits and choosing RNN