Câu 7: HPE7-S01: Advanced HPE Compute Architect

A customer has an HPE Private Cloud AI solution, running HPE AI Essentials 1.11. The customer has identified a NIM for an LLM that they want to use. The customer has imported NeMo microservices on the AI Essentials platform. The customer plans to use NeMo Customizer’s LoRA to fine-tune the LLM for their purposes. What should you recommend that the customer do to deploy the fine-tuned model on HPE Private Cloud AI with HPE Machine Learning Inference Software?

1. A. Set up a custom OpenLLM registry in which they add the fine-tuned weights.
2. B. Store the fine-tuned weights in the local S3 object store.
3. C. Use environment variables when they deploy the model to point to the NeMo entity store running on AI Essentials. — đáp án hiện tại
4. D. Submit a support request to add the fine-tuned model to the NIMs hosted on HPE Private Cloud AI.