Certified Generative AI Engineer AssociateDemo

By Databricks · Question Mode

QuestionQ27

Assembling and Deploying Applications

An AI developer team wants to fine-tune an open-weight model for exceptional performance in a code-generation use case. They are trying to select the best model to begin with. They want to minimize model-hosting costs and are using Hugging Face model cards and Spaces to explore models.

Which TWO model attributes and metrics should the team focus on for their selection?

Choose two
  • A Big Code Models Leaderboard
  • B Number of model parameters
  • C MTEB Leaderboard
  • D Chatbot Arena Leaderboard
  • E Number of model downloads last month
Explanation

The Big Code Models Leaderboard provides code-model evaluation results, so it is relevant for comparing code-generation performance. The number of model parameters is a primary indicator of inference memory and compute requirements and therefore of model-hosting cost. MTEB is intended for embedding-model evaluation, Chatbot Arena measures general chatbot preferences, and download volume measures popularity rather than the required performance and cost criteria.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!