NeMo Customizer API Microservice Container

The NeMo Customizer API microservice provides the interface and orchestration layer for customizing large language models (LLMs). While the training workloads are executed by the separate NeMo Customizer training image, this API service manages the customization jobs, provides status updates, and handles all user interactions with the customization ecosystem.

Using this API microservice, you can balance your compute requirements with your particular performance needs by selecting among a range of models, model sizes and fine-tuning techniques. The API service coordinates with the NeMo Customizer training infrastructure to create models that can easily integrate with NVIDIA NIM for LLMs. To learn more about supported customization techniques, you can read our Model Customizations tutorials.

Resources

Helm Chart | User Guide

Note: Use, distribution or deployment of this microservice in production requires an NVIDIA AI Enterprise License.

Governing Terms

The software and materials are governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.