Results for “inference”

Train and run models on Tinker (Thinking Machines) — LoRA and full fine-tuning, SFT with correct loss masking, RL/RFT with group-relative advantages and importance sampling, agentic RL over multi-turn tool-using agents, inference via the SamplingClient or the OpenAI-compatible endpoint, checkpoint management and export, every hyperparameter, and cost estimation from the live price table. Use this skill whenever the user mentions Tinker, tinker://, TINKER_API_KEY, console.tinker.ai, or the tinker CLI; wants to fine-tune, SFT, RFT, or RL a model on Tinker; asks about Tinker models, context windows, LoRA rank, sampling params, loss functions (cross_entropy, importance_sampling, ppo, cispo, dro), Datum construction, forward_backward or optim_step; wants to sample from, download, resume, merge, or export a Tinker checkpoint; or asks what a Tinker run will cost. Whenever Tinker work is initialized in a project, this skill also creates a TINKER_PRICING.md there so prices sit next to the training code. Reach for it even on vague asks like "train a model on this data" or "get inference working" when Tinker is the platform in play.

The English summary is being prepared. Showing the original description.

No Inference / Source-Locked Verification. Forces Claude to answer ONLY from user-provided materials and/or online sources actually accessed — no inference, no assumptions, no gap-filling. Every factual, legal, numerical, or procedural claim must be anchored to a cited source. Use whenever Claude reviews documents, summarises evidence, checks accuracy, drafts submissions, creates timelines, extracts facts, checks citations, analyses rules, prepares legal arguments, compares documents, verifies claims, produces chronologies, works from uploaded materials, performs legal research, checks case status, or does anything where evidential fidelity matters. Also trigger on: 'source-locked', 'no inference', 'only from the materials', 'don't assume', 'stick to the evidence', 'verify this', 'check this is right', 'work from the documents'. Overrides Claude's default tendency to fill gaps. If evidential accuracy matters, use this skill.

The English summary is being prepared. Showing the original description.

Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX Runtime, and OllamaSharp. Covers the full spectrum from classic ML through modern LLM orchestration to local inference. Use when adding classification, regression, clustering, anomaly detection, recommendation, LLM integration (text generation, summarization, reasoning), RAG pipelines with vector search, agentic workflows with tool calling, Copilot extensions, or custom model inference via ONNX Runtime to a .NET project. DO NOT USE FOR projects targeting .NET Framework (requires .NET 8+), the task is pure data engineering or ETL with no ML/AI component, or the project needs a custom deep learning training loop (use Python with PyTorch/TensorFlow, then export to ONNX for .NET inference).

The English summary is being prepared. Showing the original description.

Think and work like an expert Causal Inference Scientist. Use when a task calls for Causal Inference Scientist judgment. Reasons from structural causal models, potential outcomes, and identification logic through DAGs and do-calculus, doubly-robust estimators (AIPW/TMLE, IPTW, g-formula), and design-based methods (IV, RD, Callaway-Sant'Anna DiD, synthetic control) while treating colliders and M-bias, positivity/overlap failure, and unmeasured confounding (Rosenbaum bounds, E-values) as first-class failure modes.

The English summary is being prepared. Showing the original description.

Cerebras Inference is a hosted LLM API that runs open models on Cerebras wafer-scale chips at thousands of tokens per second, through an OpenAI-compatible endpoint. Use when a user wants the lowest-latency chat, code completion or agent loop, asks how to call the Cerebras API or SDK, needs streaming, tool calling, strict JSON schema output or reasoning control, or hits a "model not found" error from a retired Cerebras model ID.

The English summary is being prepared. Showing the original description.

因果推論・効果検証（A/B テスト / ABテスト / オンライン実験 / リフト / SRM / CUPED、観察データの処置効果 / ATE / ATT / CATE / 傾向スコア / propensity score / IPW / 二重頑健 / DML / causal forest、準実験 / 差の差 / DiD / イベントスタディ / 操作変数 / IV / 2SLS / 回帰不連続 / RDD / 合成コントロール）を実行したら必ずセットで出す図と値のルーター。 proportions_ztest, chisquare, statsmodels.stats.power, dowhy, econml, causalml, doubleml, propensity, LinearDML, IV2SLS, rdrobust, rddensity, pysyncon, treat*post がコードに現れたとき、またはユーザーが「ABテストの結果を 見て」「施策の効果を推定して」「差の差で」「傾向スコアで揃えて」「閾値前後で比較して」と言ったときに使う。SRM・ バランス・並行トレンド・first-stage に言及がなくても適用する。SKILL.md のルーティング表で設計を特定し、対応する references/<設計>.md を読んでから実行する。実験でない群間比較の検定は statistical-inference-diagnostics、 予測モデルの解釈（SHAP 等）は predictive-modeling-diagnostics を使う。

The English summary is being prepared. Showing the original description.

統計的推論（線形回帰 / 重回帰 / OLS / Lasso / Ridge / 分位点回帰、ロジスティック回帰 / ポアソン / GLM / オッズ比、 混合効果 / マルチレベル / パネル固定効果、仮説検定 / t 検定 / χ² / ANOVA / 有意差、生存時間分析 / Kaplan-Meier / Cox、 ベイズ推定 / MCMC / Stan）を実行したら必ずセットで出す図と値のルーター。sm.OLS, smf.ols, LinearRegression, LassoCV, QuantReg, sm.Logit, sm.GLM, LogisticRegression, mixedlm, PanelOLS, ttest_ind, mannwhitneyu, chi2_contingency, pingouin, lifelines, CoxPHFitter, cmdstanpy, arviz がコードに現れたとき、またはユーザーが「回帰して」「検定して」 「有意差はあるか」「生存曲線を描いて」「ベイズで推定して」と言ったときに使う。診断・残差・図に言及がなくても適用する。 SKILL.md のルーティング表で手法を特定し、対応する references/<手法>.md を読んでから実行する。A/B テスト・因果推論は causal-inference-diagnostics、予測 ML・時系列は predictive-modeling-diagnostics を使う。

The English summary is being prepared. Showing the original description.

Bridge active inference theory with robot control using K-Scale's JAX/MuJoCo stack. Use when connecting predictive coding to locomotion policies, mapping KL divergence minimization to RL training, applying mean field approximation to robotics state estimation, or implementing sim2real as inference about future observations.

The English summary is being prepared. Showing the original description.

Deploy machine learning models to production serving infrastructure using MLflow, BentoML, or Seldon Core with REST/gRPC endpoints, implement autoscaling, monitoring, and A/B testing capabilities for high-performance model inference at scale. Use when deploying trained models for real-time inference, setting up REST or gRPC prediction APIs, implementing autoscaling for variable load, running A/B tests between model versions, or migrating from batch to real-time inference.

The English summary is being prepared. Showing the original description.

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations.

The English summary is being prepared. Showing the original description.

Run 150+ AI applications in the cloud via the inference.sh platform. Triggers on "generate image with FLUX", "create video", "use Veo/Seedance", "run inference.sh", "infsh CLI", "single key for image+video+LLM". One API key covers image generation (FLUX, Reve, Seedream, Grok, Gemini), video (Veo, Wan, Seedance, OmniHuman, HunyuanVideo), LLMs (Claude, Gemini, Kimi, GLM-4), search (Tavily, Exa), 3D (Rodin), social (Twitter/X), and audio (TTS, voice cloning).

The English summary is being prepared. Showing the original description.

Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.

The English summary is being prepared. Showing the original description.

Execute model inference on GPU cloud providers. Handles code generation, deployment, execution, and result collection across HF Inference API/Endpoints, Colab, Modal, beam.cloud, Vast.ai, and RunPod. Use when running models on GPU, deploying to cloud, executing notebooks, or troubleshooting GPU execution failures. Triggers on "run on GPU", "execute model", "deploy to modal", "colab notebook", "beam deploy", "HF inference", "HF endpoints", "vast", "runpod".

The English summary is being prepared. Showing the original description.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

The English summary is being prepared. Showing the original description.

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

The English summary is being prepared. Showing the original description.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

The English summary is being prepared. Showing the original description.

Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation. Uses the terminal tool. Triggers: inference.sh, infsh, ai apps, flux, veo, image generation, video generation, seedream, seedance, tavily

The English summary is being prepared. Showing the original description.

Set up and optimize large language model inference, or response generation, on NVIDIA GPUs. Use quantization, batch processing, and multiple GPUs to improve serving performance, and expose models through a chat completion API.

• Serving a language model through a chat completion API
• Processing many prompts in batches
• Configuring quantization to reduce memory use

Configure Hermes to run AI models through Actual Computer on your own hardware. Set up either the hosted relay or a local connection, select models, verify responses, and troubleshoot request errors or empty output.

• Connecting Hermes with an Actual inference key
• Running models through a local Actual daemon
• Downloading and loading local models

Research current public information by checking original sources, recording relevant passages, dates, and URLs, and using browser interaction when needed. Cross-check important claims and clearly separate supported facts from inference.

• Checking current information against official sources
• Comparing evidence across multiple web pages
• Researching pages that require browser interaction

Connect AI agents to OmniRoute for text and image generation, speech synthesis, transcription, and web search. Use OpenAI-compatible APIs and create embeddings, numerical representations of text, through documented requests.

• Add text generation to an AI agent
• Generate or edit images from instructions
• Turn text into speech or transcribe audio

Build Bayesian models in PyMC to estimate effects and quantify uncertainty. Fit regression or hierarchical models, check sampling diagnostics, assess predictions against observed data, predict new groups, and compare models using predictive performance.

• Estimate regression effects with uncertainty
• Model differences across patients or groups
• Inspect sampling diagnostics and predictive checks

Build Python workloads on Modal for cloud execution, including GPU model training and inference, web APIs, scheduled jobs, and parallel batch processing. Configure container environments, persistent storage, and automatic scaling through the Modal SDK.

• Serving an AI model through a web API
• Running model training or fine-tuning on cloud GPUs
• Processing independent batch inputs in parallel

Review GitHub Actions workflows that run AI agents, tracing how external input reaches prompts and tools. Produce findings with evidence, severity, impact, and remediation guidance through static analysis, which examines configuration without running attacks.

• Auditing AI agent integrations in GitHub Actions
• Tracing issue and PR text into agent prompts
• Reviewing sandbox settings and tool permissions