Context window and token limits in Prompt Engineering / GenAI - Model Pipeline Trace

Model Pipeline - Context window and token limits

This pipeline shows how input text is processed in a generative AI model with a limited context window defined by token limits. It explains how the model handles input tokens, processes them, and generates output within these limits.

Data Flow - 5 Stages

1Input Text

1 sample x variable length text→Raw text input from user→1 sample x variable length text

"Hello, how are you doing today?"

↓

2Tokenization

1 sample x variable length text→Convert text into tokens (words or subwords)→1 sample x 8 tokens

["Hello", ",", "how", "are", "you", "doing", "today", "?"]

↓

3Context Window Enforcement

1 sample x 8 tokens→Limit tokens to max context window size (e.g., 8 tokens)→1 sample x 8 tokens

["how", "are", "you", "doing", "today", "?", "<pad>", "<pad>"]

↓

4Model Processing

1 sample x 8 tokens→Process tokens through transformer layers→1 sample x 8 tokens x 768 features

Tensor of shape (1, 8, 768) representing token embeddings

↓

5Output Generation

1 sample x 8 tokens x 768 features→Generate next tokens within token limit→1 sample x 5 tokens

["I", "am", "fine", ".", "<eos>"]

Training Trace - Epoch by Epoch

Loss:
2.3 |**************
1.8 |**********
1.2 |*******
0.8 |****
0.5 |**

Epochs -> 1 3 5 7 10

Epoch	Loss ↓	Accuracy ↑	Observation
1	2.3	0.15	Model starts with high loss and low accuracy on token prediction
3	1.8	0.35	Loss decreases as model learns token patterns
5	1.2	0.55	Accuracy improves steadily with training
7	0.8	0.70	Model converges with lower loss and higher accuracy
10	0.5	0.85	Final epoch shows good token prediction performance

Prediction Trace - 4 Layers

Layer 1: Tokenization

Layer 2: Context Window Enforcement

Layer 3: Transformer Layers

Layer 4: Output Generation

Model Quiz - 3 Questions

What happens if the input text exceeds the model's context window?

A The model automatically increases its context window

B Tokens beyond the limit are dropped or truncated

C The model ignores the token limit and processes all tokens

D The model returns an error and stops

Key Insight

The context window and token limits define how much text the model can consider at once. Managing these limits is crucial for efficient processing and accurate predictions in generative AI models.

Practice

1. What does the context window in a language model refer to?

easy

A. The speed at which the model generates text

B. The maximum amount of text the model can process at once

C. The number of layers in the model

D. The size of the model's vocabulary

Solution

1. Step 1: Understand the term 'context window'

   The context window is the chunk of text the model reads at one time.

2. Step 2: Relate to model processing limits

   The model cannot process more text than this window size at once.

3. Final Answer:

   The maximum amount of text the model can process at once -> Option B

4. Quick Check:

   Context window = max text processed [OK]

Hint: Context window means max text input size [OK]

Common Mistakes:

• Confusing context window with model layers
• Thinking it relates to speed
• Mixing it with vocabulary size

2. Which of the following is the correct way to check if input text fits within a model's token limit in Python?

easy

A. if len(tokenizer.encode(text)) <= token_limit:

B. if len(text) <= token_limit:

C. if len(text.split()) <= token_limit:

D. if text.length <= token_limit:

Solution

1. Step 1: Understand token counting

   Tokens are pieces of text, not just characters or words, so we must use the tokenizer.

2. Step 2: Use tokenizer to encode text

   Using tokenizer.encode(text) gives the token list; its length is token count.

3. Final Answer:

   if len(tokenizer.encode(text)) <= token_limit: -> Option A

4. Quick Check:

   Use tokenizer.encode() to count tokens [OK]

Hint: Use tokenizer.encode() to count tokens, not len(text) [OK]

Common Mistakes:

• Counting characters instead of tokens
• Counting words by splitting text
• Using incorrect syntax like text.length

3. Given a model with a token limit of 10, what will be the output of this Python code snippet?

text = "Hello world! This is AI."
tokens = tokenizer.encode(text)
print(len(tokens) <= 10)

medium

A. Error: tokenizer not defined

B. False

C. True

D. 10

Solution

1. Step 1: Check for defined variables

   The code uses tokenizer.encode(text), but tokenizer is not defined or imported.

2. Step 2: Trace execution

   Execution stops at tokens = tokenizer.encode(text) with NameError: name 'tokenizer' is not defined. No output is printed.

3. Final Answer:

   Error: tokenizer not defined -> Option A

4. Quick Check:

   Undefined tokenizer causes NameError [OK]

Hint: Check for undefined variables like tokenizer [OK]

Common Mistakes:

• Assuming tokens equal words
• Ignoring tokenizer definition
• Confusing output with token count

4. You have a model with a 50-token limit. This code throws an error. What is the likely cause?

input_text = "A very long text..."  # over 100 tokens
tokens = tokenizer.encode(input_text)
if len(tokens) > 50:
    model.generate(tokens)

medium

A. The input tokens exceed the model's token limit

B. The tokenizer.encode() function is missing parentheses

C. The if condition should be len(tokens) < 50

D. The model.generate() function cannot accept tokens directly

Solution

1. Step 1: Trace code execution flow

   Input exceeds 100 tokens, so len(tokens) > 50 is True and model.generate(tokens) executes.

2. Step 2: Check model.generate() input type

   Usually, model.generate() expects input_ids as a tensor, not raw token list from encode(), causing TypeError.

3. Final Answer:

   The model.generate() function cannot accept tokens directly -> Option D

4. Quick Check:

   model.generate() needs tensor input_ids, not list [OK]

Hint: model.generate() expects text, not token list [OK]

Common Mistakes:

• Assuming generate accepts tokens directly
• Ignoring correct token limit check
• Misreading if condition logic

5. You want to send a long document to a language model with a 1000-token limit. Which approach best ensures the model processes the entire document without errors?

hard

A. Only send the first 100 tokens to reduce load

B. Send the whole document at once and hope the model truncates it correctly

C. Split the document into chunks of 1000 tokens or less and process each separately

D. Increase the model's token limit by changing its architecture

Solution

1. Step 1: Understand token limit constraints

   The model cannot process more than 1000 tokens at once, so input must fit this limit.

2. Step 2: Choose a method to handle long text

   Splitting the document into chunks under 1000 tokens ensures all parts are processed without errors.

3. Step 3: Evaluate other options

   Sending all at once risks truncation; sending only 100 tokens loses data; changing architecture is not feasible.

4. Final Answer:

   Split the document into chunks of 1000 tokens or less and process each separately -> Option C

5. Quick Check:

   Chunking long text fits token limits [OK]

Hint: Split long text into token-sized chunks [OK]

Common Mistakes:

• Sending too long text at once
• Ignoring most of the document
• Thinking token limit can be changed easily