promptfoo/examples/amazon-sagemaker/promptfooconfig.llama-vs-mistral.yaml

# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: 'Comparison between Mistral 7B and Llama 3 on SageMaker'

prompts:
  - 'Generate a creative name for a coffee shop that specializes in {{flavor}} coffee.'
  - 'Write a short story about {{topic}} in {{style}} style. Aim for {{length}} words.'
  - 'Explain the concept of {{concept}} to {{audience}} in a way they can understand.'

providers:
  # Llama 3.2 provider
  - id: sagemaker:jumpstart:your-llama-endpoint
    label: 'Llama 3.2 (8B)'
    delay: 500 # Add 500ms delay between requests
    config:
      region: us-west-2
      modelType: jumpstart
      temperature: 0.7
      maxTokens: 256
      topP: 0.9
      contentType: 'application/json'
      acceptType: 'application/json'
      responseFormat:
        path: 'json.generated_text'

  # Mistral 7B provider
  - id: sagemaker:huggingface:your-mistral-endpoint
    label: 'Mistral 7B v3'
    delay: 500 # Add 500ms delay between requests
    config:
      region: us-west-2
      modelType: huggingface
      temperature: 0.7
      maxTokens: 256
      topP: 0.9
      contentType: 'application/json'
      acceptType: 'application/json'
      responseFormat:
        path: 'json[0].generated_text'

tests:
  - vars:
      flavor: caramel
      topic: a robot that becomes self-aware
      style: science fiction
      length: '250'
      concept: artificial intelligence
      audience: a 10-year-old
  - vars:
      flavor: lavender
      topic: a barista who can read customers' minds
      style: mystery
      length: '300'
      concept: machine learning
      audience: a senior citizen
  - vars:
      flavor: pumpkin spice
      topic: time travel to a coffee plantation in the 1800s
      style: historical
      length: '350'
      concept: neural networks
      audience: a business executive