nerdexam
Databricks

GENERATIVE-AI-ENGINEER-ASSOCIATE · Question #24

A team wants to serve a code generation model as an assistant for their software developers. It should support multiple programming languages. Quality is the primary objective. Which of the…

The correct answer is D. CodeLlama-34B. CodeLlama-34B (option D) is the correct choice because it is specifically designed and trained for code generation tasks and supports a wide range of programming languages (Python, C++, Java, JavaScript, etc.). Quality is the primary objective, and a 34B parameter model…

Generative AI Model Selection and Application

Question

A team wants to serve a code generation model as an assistant for their software developers. It should support multiple programming languages. Quality is the primary objective. Which of the Databricks Foundation Model APIs, or models available in the Marketplace, would be the best fit?

Options

  • ALlama2-70b
  • BBGE-large
  • CMPT-7b
  • DCodeLlama-34B

How the community answered

(36 responses)
  • A
    3% (1)
  • B
    8% (3)
  • C
    17% (6)
  • D
    72% (26)

Explanation

CodeLlama-34B (option D) is the correct choice because it is specifically designed and trained for code generation tasks and supports a wide range of programming languages (Python, C++, Java, JavaScript, etc.). Quality is the primary objective, and a 34B parameter model purpose-built for code will significantly outperform general-purpose or smaller models on this task. Llama2-70B (A) is a general-purpose text model not optimized for code. BGE-large (B) is an embedding model used for semantic search, not text generation. MPT-7b (C) is a small general-purpose model with limited code generation capability compared to a code-specialized 34B model.

Topics

#Generative AI Models#Code Generation#Model Selection#Databricks Foundation Models

Community Discussion

No community discussion yet for this question.

Full GENERATIVE-AI-ENGINEER-ASSOCIATE Practice