Results for “model quality”

Quantize diffusion transformers with NVIDIA ModelOpt, using FP8 or NVFP4 lower-precision numbers, and prepare the saved weights for SGLang Diffusion. Follow a workflow for loading, checking output quality, and comparing speed under matching conditions.

• Preparing ModelOpt FP8 weights for SGLang Diffusion
• Checking quality after diffusion model quantization
• Comparing BF16 and quantized generation speed

Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".

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

Check training data and machine learning models for malicious changes, including backdoors that cause unexpected behavior on specific inputs. Combine data quality checks, model analysis, and file integrity verification, then document findings and retest after remediation.

• Screening third-party data before training
• Checking downloaded model weights before deployment
• Investigating unexpected behavior on specific inputs

Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.

• Fine-tuning an embedding model for domain-specific search
• Training a model to rerank search results
• Training SPLADE or ColBERT retrieval models

Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.

• Fine-tuning an embedding model for domain-specific search
• Training a model to rerank search results
• Training SPLADE or ColBERT retrieval models

Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.

• Compare models on standard knowledge and reasoning tests
• Track model performance across training checkpoints
• Organize evaluation results for research reports

Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.

• Compare models on standard knowledge and reasoning tests
• Track model performance across training checkpoints
• Organize evaluation results for research reports

Evaluate code generation models with HumanEval, MBPP, and other benchmarks. Test generated programs, compare models across programming languages, and record pass@k scores, which estimate the chance that at least one of k solutions passes the tests.

• Comparing code generation models on shared benchmarks
• Measuring correctness across programming languages
• Evaluating models trained to follow instructions

Compress large language model weights to four bits with AWQ, a method that uses model activation patterns to limit quality loss. Follow workflows for quantization, loading compressed models, and serving them with vLLM using less GPU memory.

• Running large language models with limited GPU memory
• Quantizing a model with domain-specific text
• Serving an AWQ model with vLLM

Evaluate code generation models with HumanEval, MBPP, and multilingual benchmarks. The skill guides test execution and model comparisons using pass@k, an estimate of whether at least one of k generated solutions passes the tests.

• Compare code generation models on shared benchmarks
• Measure code generation performance across languages
• Evaluate instruction-tuned coding models

This skill should be used whenever the user mentions a "semantic model", "data model", or "dataset", or asks to "build", "model", "design", "optimize", "review", or "audit" one, or to "add a measure", "add a relationship", "create a role" / "set up RLS", "add a calculation group", "set up incremental refresh", "fix a star schema", "reduce model size", "prepare a model for Copilot / AI", or "check model quality". Covers the full lifecycle (design, build, refresh, review) and drives every operation through the `te` CLI first, then TOM (connect-pbid) or a model MCP, then TMDL authoring (the tmdl skill). Not for report visuals (use pbir-cli) or isolated DAX query tuning (use the dax skill).

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

Create HTML slides about choosing and connecting AI models in OpenDesign using your own API key. Use a terminal-style template to explain costs, quality, and model routing decisions, with speaker notes and presentation controls.

• Explaining model choices to engineers and IT teams
• Comparing model costs, quality, and routing decisions in slides
• Preparing a terminal-style presentation with speaker notes

Convert LLMs to GGUF and reduce model size through quantization, which stores weights at lower numerical precision. Prepare models for CPU or Apple Silicon inference, compare compression levels, and integrate them with local AI tools.

• Preparing an LLM for CPU-only use
• Running a local model on Apple Silicon
• Comparing model size and quality across quantization levels

Selects, deploys, and customizes AI models on Amazon SageMaker. Training or Processing jobs, fine-tuning (SFT/DPO/RLVR/RLAIF), model selection, dataset preparation, evaluation, SageMaker or Bedrock deployment, inference optimization and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing which base model to customize, fine-tune, or deploy from SageMaker JumpStart or Hub, SageMakerPublicHub, or the SageMaker public model catalog, transforming or validating training data, evaluating model quality, deploying or optimizing endpoints, configuring IAM/S3 for training, or managing SageMaker Managed MLflow. Use for endpoint health, failures, latency, logs, metrics, errors. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.

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

Expert-level air quality engineering covering pollutant sources, atmospheric dispersion, air quality standards, emission controls, and air quality modeling.

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

Autonomous model validation and benchmarking. Investigates any ML model (LLM, image gen, TTS, time series, etc.), runs it on GPU cloud, evaluates quality and performance, and generates HTML reports. Use when user asks to verify, benchmark, evaluate, or test a model. Triggers on "verify model", "benchmark", "evaluate model", "test model", "run benchmark", "model evaluation", "モデルを検証", "ベンチマーク", "モデルを試して".

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

Design dbt data transformations with clearly organized models, data quality tests, documentation, and incremental processing that updates only part of a dataset. Use it to structure analytics tables and organize a dbt project.

• Organizing a dbt project into model layers
• Adding data quality tests
• Designing incremental updates for large tables

Prepare raw credit data for pre-loan modeling by checking data quality and screening variables. Review missing values, predictive usefulness, stability, noise, and correlation, then export an Excel report with organization-level statistics and cleaning results.

• Prepare credit data before building a model
• Compare missing values and bad-sample rates across organizations
• Screen variables for usefulness, stability, and redundancy

Evaluate LLM application quality using automated scores, human reviews, and another language model as a judge. Compare models or prompts, establish baseline results, and detect quality drops through repeatable tests and statistical comparisons.

• Comparing models and prompts
• Checking quality before deployment
• Evaluating search quality in RAG applications

Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.

• Run language models with limited GPU memory
• Convert your own model to 4-bit weights
• Compare compression settings for quality and speed

Turns mathematical modeling competition problems and attachments into an implementation-ready report. It breaks down questions, examines ambiguous assumptions and data quality, and defines variables, equations, constraints, solution methods, and validation steps.

• Breaking down competition questions and their dependencies
• Comparing interpretations of ambiguous problem statements
• Reviewing attached data before modeling

Role-based multi-model strategy. The model catalog lives in a local configuration file instead of the skill text -- roles (thinker/decision-maker, long-running worker, draft generator, reviewer/acceptance, escalation), reasoning effort as an independent axis, mandatory review for draft models, provider switching for independent reviews, budgets, delegation flow, and cost/quality of small workers.

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

Use when the user wants to send the same prompt to several LLMs and compare the answers - sequentially (stopwatch, clean per-lane timing) or in parallel (true race), with optional repetitions per model, judged by the starting model across quality, correctness, completeness, instruction fidelity and latency (time is only one dimension). Triggers on /compare-race, 'model race', 'vergleiche modelle', 'gleicher prompt an mehrere modelle'.

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

Plan and review machine learning systems for production use, covering data requirements, repeatable training, quality checks, deployment, monitoring, and rollback. Produce concrete plans and review findings for moving model experiments into operational systems.

• Turning notebook experiments into reusable training pipelines
• Defining quality checks before releasing a model
• Investigating data leakage and training–serving mismatches