Use Aim's Python SDK to create local repositories and runs, track metrics/params/media/artifacts/logs, query sequences, and validate SDK instrumentation safely.
Idioma do texto original: inglês
Menu
Skills neste repositório
O SkillsMP coletou 5.368 skills de VectorSpaceLab/AREX-Skill. Abra uma skill para revisar a origem e os detalhes.
VectorSpaceLab/AREX-SkillMostrando 40 de 5.368 skills coletadas.
Use Aim's Python SDK to create local repositories and runs, track metrics/params/media/artifacts/logs, query sequences, and validate SDK instrumentation safely.
Idioma do texto original: inglês
Route AIMET install, PyTorch/ONNX quantization, GenAILab, model access, cluster/Pod, Qualcomm SDK, optimization, export, and repository tasks to focused operating guidance.
Idioma do texto original: inglês
Operate AIMET cluster and Pod workflows for GPU development, source builds, GenAILab runs, sync, exec, and cleanup.
Idioma do texto original: inglês
Run and configure AIMET GenAILab LLM/VLM quantization scorecards with Torch or ONNX backends, exports, caches, and summaries.
Idioma do texto original: inglês
Install, build, repair, and validate AIMET package environments and repository build/test workflows.
Idioma do texto original: inglês
Handle AIMET model downloads, Hugging Face tokens, GitHub Actions scorecard runs, AWS/S3 checkpoints, caches, and benchmark-result comparability.
Idioma do texto original: inglês
Use AIMET ONNX for QuantizationSimModel calibration, provider selection, encodings, QDQ export, graph passes, and ONNX PTQ utilities.
Idioma do texto original: inglês
Use AIMET analysis, mixed precision, compression, debugging, export validation, and deployment artifact workflows after core quantization setup.
Idioma do texto original: inglês
Prepare AIMET exports for Qualcomm AI Hub, QAIRT/QNN conversion, profiling, inference, and SDK command generation.
Idioma do texto original: inglês
Use AIMET Torch for model preparation, QuantizationSimModel calibration, PTQ/QAT, encodings, and Torch export workflows.
Idioma do texto original: inglês
Route Airweave tasks to the most specific sub-skill: local-development, backend-api, source-connectors, frontend-dashboard, connect-widget, mcp-search, or monke-e2e.
Idioma do texto original: inglês
Operates Airweave's backend API surface for search tiers, collections, source connections, Connect sessions, browse-tree selection, sources, webhooks, usage checks, source rate limits, and streaming search debugging.
Idioma do texto original: inglês
Operates the embeddable Connect widget iframe, client-side session UX, parent-child postMessage, OAuth popup recovery, theme updates, connection creation, folder selection, and sync progress handling.
Idioma do texto original: inglês
Operates Airweave's React dashboard: auth, organization context, API client behavior, collections, search UI, billing/admin pages, webhooks, auth providers, usage gates, and cron utilities.
Idioma do texto original: inglês
Operate the Airweave local Docker stack safely: start, reuse, restart, recreate, destroy, seed environment, check ports, and recover health failures.
Idioma do texto original: inglês
Operate the Airweave MCP search server in stdio and Streamable HTTP modes, including tool registration, collection and organization resolution, auth modes, Prometheus metrics, deployment knobs, and search-tool behavior.
Idioma do texto original: inglês
Operate Airweave's Monke connector E2E framework safely: discover connectors, understand runner flow, configs, auth, bongos, generated test data, and credentialed-test boundaries.
Idioma do texto original: inglês
Implement, validate, and troubleshoot Airweave source connectors: decorators, registry metadata, auth/config schemas, browse trees, ACLs, federated search, incremental sync, and source rate limits.
Idioma do texto original: inglês
Routes AIX360 explainability tasks across local black-box attribution, counterfactuals and certification, interpretable models, time-series explanations, datasets, and explanation-quality metrics.
Idioma do texto original: inglês
Use AIX360 for contrastive CEM/CEM-MAF explanations, black-box certification, GLANCE recourse, and order-constrained optimal-transport matching.
Idioma do texto original: inglês
Guides AIX360 dataset acquisition, local-path validation, preprocessing contracts, explanation-quality metrics, and offline troubleshooting for HELOC, COMPAS, CDC, MEPS, Ford, Sunspots, CIFAR, MNIST, CelebA, eSNLI, and related datasets.
Idioma do texto original: inglês
Choose and operate AIX360's directly interpretable models, rule learners, prototypes, model differencing, teaching explanations, and optional neural interpretable methods.
Idioma do texto original: inglês
Guide local post-hoc explanations for black-box predictors on tabular, text, image, and generic structured inputs with AIX360 0.3.0 wrappers, output checks, and local metrics.
Idioma do texto original: inglês
Use AIX360 TSICE, TSLime, and TSSaliency for local numeric explanations of univariate or multivariate time-series models, including temporal perturbations, relevant history, exogenous inputs, and integrated-gradient saliency.
Idioma do texto original: inglês
Use AiZynthFinder for retrosynthetic planning, configuration, route analysis, custom extensions, and focused development workflows.
Idioma do texto original: inglês
Create, validate, and troubleshoot AiZynthFinder configuration files, stocks, model assets, public-data setup commands, and data-tool commands.
Idioma do texto original: inglês
Extend AiZynthFinder with custom hooks, stocks, scorers, policies, plugins, search algorithms, and focused development tests.
Idioma do texto original: inglês
Run AiZynthFinder retrosynthesis planning and one-step expansion through CLI, Python APIs, and optional notebook interfaces.
Idioma do texto original: inglês
Inspect AiZynthFinder output files, route collections, reaction trees, route scores, clustering, images, and downstream summaries without rerunning a search.
Idioma do texto original: inglês
Use the ALAE repository for Adversarial Latent Autoencoder data preparation, CUDA training, checkpoint-backed generation, latent editing, and legacy metrics.
Idioma do texto original: inglês
Routes ALAE dataset preparation, TFRecord layout validation, sample-image setup, style-mixing image layout, and face-alignment workflows.
Idioma do texto original: inglês
Use ALAE checkpoints for demo, image generation, reconstructions, style mixing, traversals, and principal-direction management.
Idioma do texto original: inglês
Prepare and route safe ALAE FID, reconstruction FID, PPL, and LPIPS metric workflows.
Idioma do texto original: inglês
Train ALAE and StyleALAE with configs, TFRecords, DDP, and checkpoints.
Idioma do texto original: inglês
Build, debug, serialize, and integrate Albumentations 2.x augmentation pipelines for images, masks, bboxes, keypoints, volumes, and PyTorch-style datasets.
Idioma do texto original: inglês
Integrate Albumentations with PyTorch-style datasets, tensor conversion, optional extras, and DataLoader reproducibility.
Idioma do texto original: inglês
Build, edit, validate, seed, and debug Albumentations augmentation pipelines with Compose and composition combinators.
Idioma do texto original: inglês
Save, load, replay, inspect, and reproduce Albumentations augmentation pipelines with JSON/YAML serialization, ReplayCompose, applied-parameter tracking, custom Lambda mappings, deterministic seeds, and Hub caveats.
Idioma do texto original: inglês
Apply Albumentations pipelines safely to images, masks, bboxes, keypoints, multiple images, volumes, 3D masks, and labels without corrupting geometry or data formats.
Idioma do texto original: inglês
Select and parameterize Albumentations 2D transform families, including pixel, crop, resize, geometric, dropout, mixing/domain adaptation, spectrogram, text, target support, interpolation, and fill behavior.
Idioma do texto original: inglês