「lms」の検索結果

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

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。

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

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。

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

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。

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or 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。

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

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。

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. 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。

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

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。

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

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。

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

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。

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.

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 training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

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 fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

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。

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

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。

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom 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。

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.

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。

Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment 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。

Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.

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。

Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.

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。

Generative Engine Optimization (GEO) specialist — the technical, on-page publishing work that makes a given page or site discoverable, understandable, trustworthy, quotable, and fresh for AI answer engines (Google AI Overviews, ChatGPT Search, Bing Copilot, Perplexity). Use when asked to 'optimize this page/site for GEO', 'optimize for AI search / answer engines', 'get my page cited by ChatGPT/Perplexity', 'improve AI visibility/citability', 'write an llms.txt', 'add citation-ready structure or schema for AI answers', 'otimizar para busca com IA', or to audit/create/improve a codebase for generative search. Do NOT use for AI-driven SEO content strategy or programmatic pages at scale (use ai-seo), classic keyword/SERP ranking (use seo), accessibility (use web-accessibility), or multi-area site audits (use web-quality-audit).

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。

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

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-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG) and in-scope outbound links. Use when user mentions deep crawl website, recursive crawl, crawl a whole site, scrape entire website, scrape docs site, scrape documentation, scrape knowledge base, scrape blog, build RAG corpus, build vector database from website, knowledge base for chatbot, GPT knowledge files, llms.txt, sitemap crawl, BFS crawl, scrape with depth or page limit, include exclude URL globs, remove boilerplate, strip navigation header footer, website to markdown, website to text, multi-page extraction, bulk page scraping, clean markdown from URL, docs site to markdown corpus, site to clean corpus. Also applies to building RAG pipelines, indexing a customer site, syncing docs into a vector store, generating training corpora from any docs hub, or expanding a single start URL into a clean corpus of every reachable in-scope page.

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。

Measure real AI-engine visibility — traffic from ChatGPT, Perplexity, Claude, Gemini and which pages they cite — from actual GA4 referral data, not prompt sampling. Use when asked "AI visibility", "GEO/AEO check", "do LLMs cite us", "traffic from ChatGPT", or "how do we show up in AI search".

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。

Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文（用于「文献综述工具选型」与「一键安装/运行」）。

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。