Self-hosted LLMs (Llama, Mistral) in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a self-hosted Llama model using the Hugging Face Transformers library.

Prompt Engineering / GenAI

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

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

Allama-2-7b

Bgpt-3

Cbert-base-uncased

Dmistral-7b

Attempts:

3 left

💡 Hint

Common Mistakes

Using GPT or BERT model names instead of Llama.

The correct model name for loading a Llama model is llama-2-7b. Other options are different models or unrelated.

2fill in blank

medium

Complete the code to generate text from a loaded Mistral model using the generate method.

Prompt Engineering / GenAI

outputs = model.generate(input_ids, max_length=[1])

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

Atokenizer

Binput_ids

Cmodel

D50

Attempts:

3 left

💡 Hint

Common Mistakes

Passing variables like input_ids or tokenizer instead of an integer.

The max_length parameter expects an integer specifying the maximum number of tokens to generate, such as 50.

3fill in blank

hard

Fix the error in the code to correctly tokenize input text for a self-hosted Llama model.

Prompt Engineering / GenAI

inputs = tokenizer('[1]', return_tensors='pt')

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

Atokenizer

Bmodel

CHello, how are you?

Dgenerate

Attempts:

3 left

💡 Hint

Common Mistakes

Passing variable names or method names as strings instead of actual text.

The tokenizer expects a string input like a sentence. Passing the string 'Hello, how are you?' is correct.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps words to their lengths for words longer than 3 characters.

Prompt Engineering / GenAI

{word: [1] for word in words if len(word) [2] 3}

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

Alen(word)

B>

C<

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using the word itself as value or wrong comparison operators.

The dictionary maps each word to its length using len(word). The condition filters words with length greater than 3 using >.

5fill in blank

hard

Fill all three blanks to create a filtered dictionary of uppercase words and their lengths for words longer than 4 characters.

Prompt Engineering / GenAI

{ [1]: [2] for [3] in words if len([3]) > 4 }

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

Aword.upper()

Blen(word)

Cword

Dlen

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variable names inconsistently or wrong functions.

The dictionary uses the uppercase version of each word as key (word.upper()), the length as value (len(word)), and iterates over each word in words.

Practice

1. What is the main advantage of using self-hosted LLMs like Llama or Mistral?

easy

A. You keep full control and privacy over your data

B. They always run faster than cloud models

C. They require no installation or setup

D. They provide unlimited free internet access

Solution

1. Step 1: Understand self-hosted LLMs purpose

   Self-hosted LLMs run on your own machines, so your data stays private and under your control.

2. Step 2: Compare options

   Cloud models may send data externally; self-hosted models avoid this, ensuring privacy.

3. Final Answer:

   You keep full control and privacy over your data -> Option A

4. Quick Check:

   Privacy and control = B [OK]

Hint: Self-hosted means data stays with you, so privacy is key [OK]

Common Mistakes:

• Thinking self-hosted models are always faster
• Assuming no setup is needed
• Confusing self-hosted with cloud services

2. Which Python code snippet correctly loads a Llama model using the Hugging Face Transformers library?

easy

A. from transformers import LlamaForCausalLM; model = LlamaForCausalLM.from_pretrained('llama-model')

B. import llama; model = llama.load('llama-model')

C. from transformers import MistralModel; model = MistralModel.load('llama-model')

D. model = load_model('llama-model')

Solution

1. Step 1: Identify correct library and class

   The Hugging Face Transformers library uses LlamaForCausalLM to load Llama models.

2. Step 2: Check method to load model

   from_pretrained is the standard method to load pretrained models in Transformers.

3. Final Answer:

   from transformers import LlamaForCausalLM; model = LlamaForCausalLM.from_pretrained('llama-model') -> Option A

4. Quick Check:

   Transformers + from_pretrained = C [OK]

Hint: Use Transformers library and from_pretrained to load models [OK]

Common Mistakes:

• Using wrong import names
• Calling non-existent load methods
• Confusing Mistral and Llama classes

3. Given this code snippet using a Mistral model, what will be the output type of output?

from transformers import MistralForCausalLM, MistralTokenizer
model = MistralForCausalLM.from_pretrained('mistral-base')
tokenizer = MistralTokenizer.from_pretrained('mistral-base')
inputs = tokenizer('Hello world', return_tensors='pt')
outputs = model.generate(**inputs)
output = tokenizer.decode(outputs[0])

medium

A. An error because generate is not defined

B. A tensor of token IDs

C. A list of token probabilities

D. A decoded string of generated text

Solution

1. Step 1: Understand model.generate output

   model.generate returns token IDs as tensors representing generated text tokens.

2. Step 2: Decode tokens to string

   tokenizer.decode converts token IDs to a readable string.

3. Final Answer:

   A decoded string of generated text -> Option D

4. Quick Check:

   generate + decode = string output [OK]

Hint: generate returns tokens; decode converts tokens to string [OK]

Common Mistakes:

• Thinking output is raw tensor
• Confusing probabilities with tokens
• Assuming generate method is missing

4. You try to load a Llama model with this code but get an error:

from transformers import LlamaForCausalLM
model = LlamaForCausalLM.load('llama-model')

What is the likely cause of the error?

medium

A. LlamaForCausalLM cannot be imported from transformers

B. The model name 'llama-model' is invalid

C. The method load() does not exist; should use from_pretrained()

D. You need to install the Mistral library first

Solution

1. Step 1: Check method names in Transformers

   Transformers models use from_pretrained() to load models, not load().

2. Step 2: Identify error cause

   Using load() causes AttributeError because it is not defined for LlamaForCausalLM.

3. Final Answer:

   The method load() does not exist; should use from_pretrained() -> Option C

4. Quick Check:

   Use from_pretrained, not load [OK]

Hint: Use from_pretrained() to load models, not load() [OK]

Common Mistakes:

• Assuming load() is valid method
• Blaming model name without checking method
• Confusing Llama and Mistral imports

5. You want to run a self-hosted Llama model on your local machine but it has limited RAM. Which approach helps reduce memory usage while keeping reasonable performance?

hard

A. Use a cloud service instead of local hosting

B. Use quantization to reduce model size and load with 8-bit precision

C. Run the model on CPU without any batching

D. Load the full 32-bit model without any optimization

Solution

1. Step 1: Understand memory constraints

   Limited RAM means loading full 32-bit models is heavy and slow.

2. Step 2: Apply quantization

   Quantization reduces model size by using lower precision (e.g., 8-bit), saving memory and keeping decent speed.

3. Step 3: Evaluate other options

   Loading full model wastes memory; CPU without batching is slow; cloud is not self-hosted.

4. Final Answer:

   Use quantization to reduce model size and load with 8-bit precision -> Option B

5. Quick Check:

   Quantization saves memory and keeps performance [OK]

Hint: Quantize models to 8-bit for less RAM use [OK]

Common Mistakes:

• Loading full 32-bit model ignoring RAM limits
• Running without batching causing slow speed
• Switching to cloud defeats self-hosting purpose