SnowPro Specialty Gen AI GES-C01Demo

Question

A Gen AI Specialist has deployed a base model as an LLM in a production environment for a proof of concept. The model is larger and more expensive than other base models.

How can the Specialist lower production costs without affecting performance for the limited tasks needed to support the proof of concept?

A Use Snowflake Cortex Search to limit the number of context documents.
B Use Snowflake Cortex Agents to ensure the base model is concise
C Use Snowflake Cortex Fine-tuning on a different base modal
D Provide a semantic model to ensure the LLM is able to interpret the prompts

Explanation

Snowflake Cortex Fine-tuning customizes a pre-trained base model for specialized tasks. Fine-tuning a smaller, lower-cost base model for the limited required tasks can retain the needed task performance while reducing production inference costs. Snowflake documents that available LLMs vary in capability, latency, and cost, and that fine-tuning creates task-specific customized adapters.

Learn more

SnowPro Specialty Gen AI GES-C01Demo

AstroTutor

Notes

Readiness

QuestionQ61

Community Discussion