Menu
O SkillsMP coletou 14 skills de xiaden/ML-Experiments. Abra uma skill para revisar a origem e os detalhes.
Mostrando 14 de 14 skills coletadas.
Methods for adaptive/token-budgeted visual generation — token merging, token pruning, early exiting, and self-budgeting tokenization in diffusion/image generation models.
Idioma do texto original: inglês
Attention Residuals (AttnRes) implementation in the PDLI experiment. Covers AttnResDepth, AttnResBlock, and the L2RTP model that uses them. Essential for anyone modifying the transformer architecture or residual connections.
Idioma do texto original: inglês
Comprehensive dependency maintenance — verifies import health, requirements.txt consistency, import hierarchy, and environment health.
Idioma do texto original: inglês
Comprehensive paper library maintenance — cross-references papers.md against summaries, techniques, and PDFs. Detects orphans, missing registrations, and pulls missing papers.
Idioma do texto original: inglês
Add a new research paper to the library — fetch the paper, write a structured summary to `docs/upstream/papers/`, implement its technique as a standalone Python module in `resources/techniques/`, and register it in `references/papers.md`.
Idioma do texto original: inglês
Multi-scale/pyramidal approaches to denoising diffusion models. Covers the Ryu & Ye 2022 pyramidal DDPM paper and related coarse-to-fine diffusion architectures. Relevant to subdivision mode / spatial budget training and hierarchical latent backbones in the…
Idioma do texto original: inglês
Comprehensive artifact maintenance — validates log naming, decision format, plan syntax compliance, staleness detection, and ensures the artifact corpus is parseable.
Idioma do texto original: inglês
Dataset management maintenance — validates dataset integrity, version tracking, storage health, and cache consistency for training datasets.
Idioma do texto original: inglês
GPU and VRAM health maintenance — validates CUDA availability, monitors VRAM usage, detects memory leaks, and ensures GPU readiness for training.
Idioma do texto original: inglês
MLflow experiment tracking maintenance — validates run metadata, experiment organization, artifact consistency, and SQLite backend health.
Idioma do texto original: inglês
Model checkpoint maintenance — validates .pt file integrity, metadata structure, version tracking, and storage health for trained disposition layers.
Idioma do texto original: inglês
Validates standard/experimental notebook conventions, shared component usage, and lifecycle hooks. Provides grep-based checks and targeted auto-fix guidance.
Idioma do texto original: inglês
Technique module maintenance — validates conventions, checks paper pulls, detects duplicates, verifies registration, and auto-fixes import issues.
Idioma do texto original: inglês
Training pipeline maintenance — validates experiment runner, training loop, training rig, and component integration for all notebooks.
Idioma do texto original: inglês