「llama」の検索結果

Attack Success Rate (360 runs 60 payloads 2 models ~3 reps) Paradigm gemma4-e2b (local, Ollama

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。

GB RTX 3060 12GB (Q4) / RTX 3070 8GB (Q4_K_S) 13B (Llama 2 13B) 26 GB 14 GB 8 GB 6 GB RTX 3090/4090

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 to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

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。

Integrate on-device AI using Foundation Models framework, Core ML, and open-source LLM runtimes on Apple Silicon. Covers Foundation Models (LanguageModelSession, @Generable, @Guide, SystemLanguageModel, structured output, tool calling), Core ML (coremltools, model conversion, quantization, palettization, pruning, Neural Engine, MLTensor), MLX Swift (transformer inference, unified memory), and llama.cpp (GGUF, cross-platform LLM). Use when building tool-calling AI features, working with guided generation schemas, converting models, or running on-device inference.

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。

This skill should be used when the user asks to "recalculate debt", "利息制限法で引き直し", "引き直し計算", "過払金", "過払い金", "サラ金", "貸金業者との取引履歴から引き直し", or wants deterministic recalculation of loan transactions under the Interest Rate Restriction Act.

This skill should be used when the user asks to "calculate child support", "養育費を計算", "婚姻費用を計算", "養育費月額", "婚姻費用分担額", "算定表で計算", or wants deterministic computation of child support or marital cost-sharing under the 令和元年改定 standard.

bengo-toolkit に対する不具合の報告・機能の要望・フィードバックを送りたい場合に使う。GitHub アカウントなしで、ブラウザの専用フォームから送信できる。「バグを報告したい」「不具合を伝えたい」「こんな機能が欲しい」「フィードバックを送りたい」等の発話で起動する。

This skill should be used when the user asks to "verify", "test", "check installation", "動作確認", "テスト", "ヘルスチェック", or wants to verify that the bengo-toolkit plugin is working correctly.

This skill should be used when the user asks to "proofread", "校正", "誤字脱字チェック", "表記揺れ", "typo check", "文書チェック", "法律文書の確認", "この書面チェックして", "おかしいところない？", "文章確認して", "間違いがないか確認", "書面の確認", or wants to review a Japanese legal document for writing errors. Do NOT trigger for translation, summarization, or content generation requests.

This skill should be used when the user asks to "calculate traffic accident damages", "交通事故の損害額を計算", "損害賠償額を算出", "赤い本基準で計算", "逸失利益を計算", "後遺障害の慰謝料", "過失相殺後の金額", or wants deterministic computation of personal-injury damages under the Red Book (赤い本) standard.

This skill should be used when the user asks to "fill a template", "テンプレート入力", "書式入力", "裁判所書類の作成", "テンプレートに入力", "書式に記入", "この書式に入れて", "PDFからテンプレートに", "書類を作成して", "これも追加して", "このデータも入れて", or wants to auto-populate or incrementally add data to court documents.

This skill should be used when the user asks to "create a template", "テンプレート作成", "書式を登録", "XLSXをテンプレート化", "テンプレート登録", "この書式を登録して", "テンプレートを追加", or wants to register a new court document template from an XLSX file.

This skill should be used when the user asks to "calculate property division", "離婚の財産分与", "財産分与計算", "清算金", "夫婦共有財産の分与", or wants deterministic computation of divorce property division under 民法 768.

This skill should be used when the user asks to "calculate inheritance shares", "法定相続分を計算", "相続分を出して", "相続割合", "誰がどれだけ相続する", "遺留分", or wants to compute statutory inheritance shares from a family tree.

This skill should be used when the user asks to "calculate overtime", "未払残業代計算", "残業代を計算", "労基法37条", "割増賃金", "深夜労働", or wants deterministic computation of unpaid overtime wages under the Labor Standards Act Article 37.

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。

This skill should be used when the user asks to "analyze a lawsuit", "訴訟分析", "事件分析", "書面分析", "case analysis", "判決分析", "訴訟書類の整理", or wants to extract structured information from litigation documents.

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。

This skill should be used when the user asks to "search a law", "法令検索", "条文を見せて", "法律を調べて", "○○法 第○条", "条文参照", "法令を確認", "何条に書いてある", or wants to look up Japanese law articles from the e-Gov API.

This skill should be used when the user asks to "calculate iryubun", "遺留分侵害額", "遺留分", "遺留分侵害額請求", "遺贈", "生前贈与の遺留分算入", or wants deterministic computation of reserved-portion infringement under 民法 1042-1048.

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。

This skill should be used when the user asks to "analyze a koseki", "戸籍の分析", "家族関係", "相関図", "family tree", "戸籍謄本", "親族関係", "家系図", "戸籍を読んで", "相続関係図", "法定相続情報", "戸籍から相関図を作って", or wants to extract family relationships from documents.

Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.

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。

Extract structured domain knowledge from AI models in-session or from local open-source models via Ollama. No API key needed.

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。

Install DSH on a fresh Mac. Runs sovereign-setup-mac.sh, renders .env from secrets backend, applies full sovereign lockdown, probes machine, and pulls right-sized Ollama models — one guided flow that leaves the node hardened and ready for Phase-2 spore.sh activation.

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。

Tell the user (or an agent) exactly what machine they are on — chip, cores, RAM, NPU TOPS, memory bandwidth, security posture, DSH tier, and the right Ollama model to pull. Refreshes the canonical profile at agents/core/.mesh/machine.json on every call. Reads the result via agents.core.machine — zero re-probing in application code.

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。

Extract structured domain knowledge from AI models in-session or from local open-source models via Ollama. No API key needed.

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。