Results for “model-monitoring”

Fine-tune open models or Gemini models using Agent Platform infrastructure, from environment setup through data preparation, job configuration, monitoring, and deployment.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Manage machine learning models in the Agent Platform Model Registry: list, describe, upload, update, and delete models and their versions.

ML pipeline design — data versioning, experiment tracking, deployment patterns, drift monitoring. Use when building an ML pipeline from data to deployment, setting up MLOps tooling (DVC, MLflow, model registry), choosing deployment patterns (shadow, canary, A/B), or designing monitoring for drift and degradation.

Guides machine learning development with experiment tracking, hyperparameter optimization, model registry, and MLOps pipeline integration.

Monitor cloud infrastructure and applications using metrics, logs, and traces to provide real-time observability into performance, health, and reliability. Use when the user requests cloud monitoring or provides relevant inputs for this workflow.

Deploy a trained model to serving with versioning, shadow or canary rollout, and a tested rollback path.

Deploy trained machine learning models as production-ready services using REST APIs, containers, serverless functions, and orchestration platforms. Use when the user requests model deployment or provides relevant inputs for this workflow.

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow.

MLOps lead for deployment, monitoring, and scaling. Use when the user asks to talk to McGonagall, requests deployment help, or needs CI/CD for AI systems.

Create deployment-ready handoff docs: model card, inference contract, and monitoring requirements. Use when: (1) transferring from DS to engineering, (2) defining SLIs/SLOs, (3) documenting retraining triggers. NOT for: directly provisioning cloud infra.

Defines service level objectives, creates error budget policies, designs incident response procedures, develops capacity models, and produces monitoring configurations and automation scripts for production systems.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.