# H2O MLOps  Enterprise Model Registry & Hugging Face | Part 8 Integration | Part 8

## Метаданные

- **Канал:** H2O.ai
- **YouTube:** https://www.youtube.com/watch?v=hRJ0_uTzWRY
- **Дата:** 08.04.2026
- **Длительность:** 1:31
- **Просмотры:** 50

## Описание

How H2O MLOps centralizes model governance with a version-controlled registry supporting both native and third-party models.

Managing a growing portfolio of production models requires a structured, searchable registry with full version history. H2O MLOps provides exactly that—capturing training metrics, validation scores, feature importance, and metadata tags for every registered model. Importantly, the platform is not restricted to H2O-native models: teams can import MLflow models complete with package dependencies, enabling unified deployment, monitoring, and governance across all ML assets from one platform.

Technical Capabilities & Resources

➤  Internal Model Repository: Register Driverless AI models with complete version history, scoring artifacts, and custom taxonomy tags.
🔗 https://docs.h2o.ai/mlops/models/understand-models

➤  Third-Party & MLflow Integration: Import and manage MLflow and external framework models alongside native H2O models.
🔗 https://docs.h2o.ai/mlops/models/mlflow-model-support

➤  Supported Third-Party Models: Review the full list of supported external model frameworks.
🔗 https://docs.h2o.ai/mlops/models/mlflow-model-support#supported-third-party-models

## Содержание

### [0:00](https://www.youtube.com/watch?v=hRJ0_uTzWRY) Segment 1 (00:00 - 01:00)

As your AI program grows, you'll go from one model in production to dozens or hundreds. Managing that portfolio requires a proper model repository. Let me show you how we handle model management and integration with the broader ML ecosystem. Our MLS platform provides a comprehensive model repository. Each registered model has a complete profile, not just a scoring artifact, but training metrics, validation scores, feature importance, tags, comments, and links back to the original experiment. Version history is first class. You can see every version of this model that we've ever trained, performance metrics for each version, and when it was registered and who registered it. This version control is essential for reproducibility and governance. And you're not only locked into H2O trained models. You can register models from driverci with a click, but you can also import MLflow models, models trained in other frameworks or models built completely outside of our ecosystem. ML flow has become the standard for model packaging in the industry, but we fully support this format. You can import these models with their package dependencies using a requirements file, register them in a repository, deploy them through our infrastructure, and monitor them with our observability tools. Metadata and tags help you organize a growing model portfolio. You can tag models by business unit, use case, risk level, or any taxonomy that makes sense for your organization.

---
*Источник: https://ekstraktznaniy.ru/video/45945*