2,272 件 ・ 関連度順
概要と使いどころ
Guide for training outputs, metrics logging, logtree reports, tracing/profiling, and debugging training runs. Use when the user asks about training logs, metrics, debugging, tracing, profiling, timing, Gantt charts, or understanding training output files.
日本語の概要は準備中です。原文の説明を表示しています。
Curate Busabase training examples, create immutable dataset snapshots, run reproducible LoRA or QLoRA fine-tunes on a local Apple Silicon Mac with MLX-LM, compare the untouched baseline and adapter on locked evaluations, and register approved adapters. Use when the user wants to train, fine-tune, evaluate, compare, promote, or manage a local language model with Busabase as the workflow source of truth. Do not use for RAG-only knowledge retrieval, cloud training, or training a foundation model from scratch.
日本語の概要は準備中です。原文の説明を表示しています。
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
日本語の概要は準備中です。原文の説明を表示しています。
Build training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. Use when formatting production logs into SFT data, distilling from frontier APIs, or preparing data for fine-tuning. Covers JSONL formatting, data quality validation, deduplication, and train/eval splitting.
日本語の概要は準備中です。原文の説明を表示しています。
Assembles microbial-community sequencing into metagenome-assembled genomes (MAGs) with metaFlye (ONT), metaSPAdes/MEGAHIT (Illumina), and hifiasm-meta/metaMDBG (PacBio HiFi), then recovers genomes via multi-binner consolidation (MetaBAT2, MaxBin2, CONCOCT, SemiBin2, VAMB -> DAS_Tool) and QCs them against MIMAG with CheckM2, GUNC, and GTDB-Tk. Covers why a metagenome is not a genome (uneven coverage, micro-diversity, strain collapse to consensus), differential-coverage binning, co-assembly vs per-sample, the rRNA-operon collapse that fails short-read MAGs, and strain resolution with inStrain. Use when reconstructing genomes from a microbiome, soil, ocean, or gut community, recovering MAGs, or resolving strain-level variation.
日本語の概要は準備中です。原文の説明を表示しています。
Assembles microbial-community sequencing into metagenome-assembled genomes (MAGs) with metaFlye (ONT), metaSPAdes/MEGAHIT (Illumina), and hifiasm-meta/metaMDBG (PacBio HiFi), then recovers genomes via multi-binner consolidation (MetaBAT2, MaxBin2, CONCOCT, SemiBin2, VAMB -> DAS_Tool) and QCs them against MIMAG with CheckM2, GUNC, and GTDB-Tk. Covers why a metagenome is not a genome (uneven coverage, micro-diversity, strain collapse to consensus), differential-coverage binning, co-assembly vs per-sample, the rRNA-operon collapse that fails short-read MAGs, and strain resolution with inStrain. Use when reconstructing genomes from a microbiome, soil, ocean, or gut community, recovering MAGs, or resolving strain-level variation.
日本語の概要は準備中です。原文の説明を表示しています。
Work with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFace Transformers. This skill should be used when fine-tuning pre-trained models, performing inference with pipelines, generating text, training sequence models, or working with BERT, GPT, T5, ViT, and other transformer architectures. Covers model loading, tokenization, training with Trainer API, text generation strategies, and task-specific patterns for classification, NER, QA, summarization, translation, and image tasks. (plugin:scientific-packages@claude-scientific-skills)
日本語の概要は準備中です。原文の説明を表示しています。
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
日本語の概要は準備中です。原文の説明を表示しています。
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
日本語の概要は準備中です。原文の説明を表示しています。
Design RL simulation sandboxes, trajectory datasets, QLoRA/LoRA adaptation plans, eval harnesses, and rollback unhooks for agents learning specific coding behaviors beyond the base model. Use when building or reviewing tool-use training loops, offline trajectories, reward functions, self-improvement harnesses, or Port Daddy agent behavior curricula. NOT for generic ML tutorials, full model training operations, or production deployment without eval gates and safety unhooks.
日本語の概要は準備中です。原文の説明を表示しています。
機械学習のない既存アプリに、推薦・分類・予測などを追加するための手順を整理します。課題とデータの確認から、最初のモデルの学習・評価・組み込みまでを支援します。
文章をAIが扱う小さな単位に分け、大量のテキスト処理や独自の語彙学習を支援するスキル。分割結果と元の文章の位置対応、入力の長さ調整も扱います。
A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.
日本語の概要は準備中です。原文の説明を表示しています。
A first-30-days onboarding module for new hospitality hires — the behaviors, the practice, the checks, and the manager follow-up. Built as a decision-grade professional training deck for new hires, managers.
日本語の概要は準備中です。原文の説明を表示しています。
Train RuView models — camera-free WiFlow pose (10 sensor signals, no labels), camera-supervised pose (MediaPipe + ESP32 CSI → 92.9% PCK@20, ADR-079), RuVector contrastive embeddings (AETHER, ADR-024), domain generalization (MERIDIAN, ADR-027), local SNN environment adaptation, plus GPU training on GCloud and Hugging Face publishing. Use when building, fine-tuning, evaluating, or shipping a model.
日本語の概要は準備中です。原文の説明を表示しています。
Deep learning framework (PyTorch Lightning / lightning package). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
日本語の概要は準備中です。原文の説明を表示しています。
Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying chat templates, configuring sequence packing, generating synthetic training data, or writing a dataset card before a run.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
日本語の概要は準備中です。原文の説明を表示しています。
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
日本語の概要は準備中です。原文の説明を表示しています。
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
日本語の概要は準備中です。原文の説明を表示しています。
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
日本語の概要は準備中です。原文の説明を表示しています。
Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehouse vs lakehouse vs mesh, build-vs-buy), B2B customer-data-as-asset valuation and M&A readiness, data team org evolution. Use when deciding whether to train models on customer data, choosing data architecture, valuing data for fundraising or M&A, sequencing data hires, or when user mentions CDO, chief data officer, data strategy, data mesh, lakehouse, training data, data product, data monetization, or customer data asset. NOT a tactical data engineering skill — strategic decisions only.
日本語の概要は準備中です。原文の説明を表示しています。