“Model inference”

Compress large language models using knowledge distillation from teacher to student models.

Add a new AI model to a provider (anthropic, openai, groq, cerebras).

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI…

Choose OpenRouter models and routers, query live catalog data, use structured outputs and batch inference, and debug routing with metadata.

Route ClearerVoice-Studio tasks for ClearVoice inference, SpeechScore metrics, and speech-model training or data-preparation workflows.

Computer vision engineering workflow for dataset design, model selection (detection/segmentation/classification), evaluation, inference optimization, and…

Synthesize a person's voice/persona from their content; cache it.

Route BiRefNet image segmentation, matting, inference, configuration, training, evaluation, and model-export workflows.

Selects, deploys, and customizes AI models on Amazon SageMaker.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces…

Use when a task would benefit from a secondary model call through the local MCP tool lane, especially for Hugging Face or OpenAI-compatible inference…

Manage and fetch models from the Infip API.

Use when a CTF challenge centers on AI or LLM security rather than a conventional web, crypto, or reverse-only path.

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems.

Scores binary predictions (Brier, log loss, ECE, MCE, AUROC, accuracy, reliability bins, per-cohort) or saved categorical outputs joined to retained targets…

Test availability, benchmark speed, and add a new model to any OpenAI-compatible provider in models.json.

QA financial models for formula errors, hardcodes, date logic, sign conventions, circularity, balance-sheet integrity, scenario switches, units, currencies…

Author the TLA+ abstract behavioural spec for an rd-flow workspace.

Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl.

Create a reduced (fewer-layer) version of a large HuggingFace model for fast testing and debugging.

Team initialization flow (Phase 1 proposal + Phase 2 creation)

WPP semantic-model wrapper over Fabric semantic-model-authoring.

Set up AI Runway on AKS — from bare cluster to running model.

Find Earth2Studio models, data sources, and examples for a weather/climate use case.