Self-hosted LLMs (Llama, Mistral) in Prompt Engineering / GenAI - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does 'self-hosted LLM' mean?

A self-hosted LLM is a large language model that you run on your own computer or server instead of using a cloud service. It gives you full control over the model and data.

beginner

Name two popular self-hosted LLMs.

Two popular self-hosted LLMs are LLaMA and Mistral. They are open models you can run locally or on your own servers.

intermediate

Why might someone choose to use a self-hosted LLM like Llama or Mistral?

People use self-hosted LLMs to keep data private, avoid cloud costs, customize models, and have faster access without internet delays.

intermediate

What is a key challenge when running self-hosted LLMs?

A key challenge is needing powerful hardware like GPUs and enough memory to run large models efficiently.

advanced

How do Llama and Mistral differ in their design or use?

LLaMA models focus on being efficient and open for research, while Mistral models aim for high performance with fewer parameters, making them faster and lighter.

What is a main advantage of self-hosting an LLM?

A Automatic cloud updates

B No need for any hardware

C Full control over data and model

D Unlimited free usage

Self-hosting gives you full control over your data and the model, unlike cloud services.

Which hardware is usually needed to run self-hosted LLMs efficiently?

A Smartphone

B Powerful GPU and enough RAM

C Tablet

D Basic laptop CPU

Large language models require powerful GPUs and enough memory to run well.

Llama and Mistral are examples of what kind of models?

A Self-hosted LLMs

B Image recognition models

C Cloud-only LLMs

D Speech-to-text models

LLaMA and Mistral are self-hosted large language models.

Which is NOT a reason to use a self-hosted LLM?

A Data privacy

B Avoiding cloud fees

C No need for internet

D No hardware requirements

Self-hosted LLMs require hardware, so 'no hardware requirements' is incorrect.

Mistral models are designed to be:

A Lightweight and fast

B Very large and slow

C Only for image tasks

D Closed source

Mistral models focus on being lightweight and fast for better performance.

Explain what a self-hosted LLM is and why someone might want to use one.

Think about running the model on your own computer instead of online.

Compare Llama and Mistral models in terms of their design goals and typical use cases.

Focus on what makes each model special.

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