Results for “model-inference”

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers.

Use Heroku Managed Inference and Agents with the current Heroku AI workflow. Use when the agent needs to install or inspect the Heroku AI CLI plugin, provision Heroku inference access on the current standard plan, review the latest Managed Inference model catalog, attach model resources, make test inference calls, or review Heroku-managed AI model operations.

Train and run Mamba state-space models with O(n) complexity, achieving faster inference and longer context than Transformers.

Manages the lifecycle of large language models in production, covering model versioning, prompt management, inference optimization, and cost control.

Load pre-trained models from Hugging Face Hub, run pipeline inference, generate text, and fine-tune models on NLP, vision, audio, and multimodal tasks using the Transformers library.

Authenticates and connects to Google Cloud Agent Platform for inference with Gemini and third-party OpenMaaS models (Llama, DeepSeek, Qwen). Generates code for multiple SDKs, configures endpoints, and troubleshoots common errors.

Bayesian modeling and probabilistic programming with PyMC — hierarchical models, MCMC (NUTS) sampling, variational inference, LOO/WAIC model comparison, and posterior predictive checks. Use when fitting Bayesian or hierarchical models, estimating posteriors and credible intervals, running probabilistic inference, or comparing models with LOO/WAIC. Part of the AlterLab Academic Skills suite.

Runs large language models locally with Ollama, including model management, custom Modelfiles, and API integration. Use for private, offline LLM inference.

Access 100+ LLMs including Claude, Gemini, Kimi, and GLM via the inference.sh CLI with automatic fallback and cost optimization.

Generate AI avatar and talking head videos using inference.sh CLI with models like P-Video-Avatar, OmniHuman, Fabric, and PixVerse.

Generate music and songs using ElevenLabs, Diffrythm, and Tencent Song Generation models via the inference.sh CLI.

Generate videos from text, images, or references using 40+ AI models via the inference.sh CLI.

Start, query, and stop a TAO inference microservice for a specific network architecture by delegating container execution to the appropriate platform skill.

Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.

Entrena modelos de machine learning con Scikit-learn, LightGBM y XGBoost, desde un baseline hasta un modelo productivo con validación robusta y explicabilidad.

Recommend model families and validation strategy based on data, constraints, and objective. Use when: (1) choosing algorithms, (2) balancing bias/variance, (3) planning benchmark baselines. NOT for: final legal/compliance sign-off.

"Make it interpretable" is four different requests.

Convert and quantize models to GGUF format for efficient CPU/GPU inference with llama.cpp, supporting 2-8 bit quantization and Apple Silicon acceleration.

Estimates the memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub, using HTTP Range requests without downloading weights.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Plan which model tier handles which work BEFORE execution begins — a high-cognition model deeply understands the problem, lays the foundations, then emits a modular plan assigning each module the cheapest tier that can safely execute it, with escalation tripwires and one-way-door protection. Advisory only: it announces "next module → tier X / model Y" at each boundary and the HUMAN switches models — harnesses like Cursor cannot switch mid-run. Load when the user asks which model to use, wants a model plan, model tiers, model-tier routing, assign models to tasks or modules, says "cheap model got stuck", "which model for this task", "cost-efficient model choice", or when implementation-plan / problem-to-plan need a model: tier column. NOT dynamic-routing (plan-path selection after failure) — this skill assigns cognition tiers to work.

TRAK: Attributing Model Behavior at Scale

Surface beliefs, assumptions, stories, and values shaping a system. Use when deeper mental models need examining with care and evidence.

Generate images using FLUX models via the inference.sh CLI, supporting text-to-image, image-to-image, and LoRA fine-tuning.

通用跨模型审查：Review LLM 对任意研究制品进行独立评审，输出结构化评分、wiki 实体映射与改进建议

Cross-model benchmark for gstack skills. (gstack)

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Build logic models linking activities to impact. TRIGGERS - Use when user needs help with logic-model related tasks.

Build and sharpen a project's domain model — a CONTEXT.md glossary and ubiquitous language. Use when pinning down terminology, or the agent "uses the wrong words". Repo decision-memory system (INDEX.md, rejected alternatives) → docs-adr.