Update Single and Multi-Model Evaluation

[Koon-Kiat]

Update Single and Multi-Model Evaluation

Description

This enhancement involves updating the single and multi-model evaluation process to improve structure and functionality. Modularizing the code will help with maintainability, and fixing any identified bugs will improve accuracy.

Motivation

Modularizing the evaluation code allows for better readability, more straightforward debugging, and easier future expansion. This enhancement will ensure more accurate results and a streamlined evaluation process.

Key Changes

• Separate the single-model and multi-model evaluation processes into distinct functions.
• Introduce better configuration options to select models for evaluation.
• Add documentation and examples for using these evaluation functions.

Alternatives Considered

• Retaining the current structure but adding comments and minor tweaks for clarity.
• Using an external library for evaluation, though it might not fully align with the project’s requirements.

Additional Context

This enhancement addresses issue #3 and supports future scalability. Related improvements include documentation updates for both evaluation functions and any new metrics added.