2,953 件 ・ 関連度順
概要と使いどころ
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.
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。
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
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。
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.
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。
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.
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。
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
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。
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic 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。
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.
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。
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
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 interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
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。
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
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。
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
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。
Designs incremental migration strategies, identifies service boundaries, produces dependency maps and migration roadmaps, and generates API facade designs for aging codebases. Use when modernizing legacy systems, implementing strangler fig pattern or branch by abstraction, decomposing monoliths, upgrading frameworks or languages, or reducing technical debt without disrupting business operations.
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 or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
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。
Toggle which skills are surfaced — apply a profile, list, or disable a cluster without reinstall
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。
Guided customization of your litigation practice profile — change one thing without re-running the whole cold-start interview. Adjust practice role, side (plaintiff / defense / mixed), risk calibration, landscape, house style, escalation contacts, severity vocabulary, or matter workspace paths. Use when the user says "change my [thing]", "update my profile", "edit my config", or "customize".
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。
First-pass privilege log review — make the obvious privilege calls and flag the hard ones for attorney review without making close calls. Use when the user says "review the privilege log", "priv log", "check privilege on these docs", or has a log to QA before production.
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。
Close a matter — capture outcome, final exposure, and lessons, then archive it out of the active portfolio without deleting the record. Use when the user wants to close a matter, says "[matter] is done", or needs to record a settlement, dismissal, judgment, withdrawal, or consolidation outcome.
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。
Guided customization of your product counsel practice profile — change one thing without re-running the whole cold-start interview. Adjust risk calibration, escalation contacts, launch review framework, marketing claims posture, or matter workspace paths. Use when the user says "change my [thing]", "update my profile", "edit my framework", "retune my calibration", or "customize".
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。
Guided customization of your regulatory practice profile — change one thing without re-running the whole cold-start interview. Adjust watched regulators, policy library index, materiality threshold, gap response process, feed configuration, or matter workspace paths. Use when the user says "change my [thing]", "add a regulator", "update my watchlist", "edit my threshold", or "customize".
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。
Guided customization of your privacy practice profile — change one thing without re-running the whole cold-start interview. Adjust risk posture, escalation contacts, DPA playbook, privacy policy commitments, PIA house style, DSAR process, or matter workspace paths. Use when the user says "change my [thing]", "update my profile", "edit my playbook", or "customize".
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。
Manage matter workspaces for multi-client practices — create, list, switch, close, or detach the active matter. Use when the user wants to create a new matter workspace, switch the active matter, list matters, archive a matter, or work at practice-level only without an active matter.
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。
Guided customization of your legal clinic profile — change one thing without re-running the whole cold-start interview. Adjust clinic profile, jurisdiction, supervision style, practice-area templates, semester configuration, or output safeguards. Use when the user says "change my [thing]", "new semester", "add a practice area", "update my config", or "customize".
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。
Disable a community skill installed through the hub without removing its files. Use when the user wants to temporarily quiet a community skill ("disable [skill]"), stop its hooks from firing while keeping its config, or re-enable a previously disabled skill.
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。