'model merging' 검색 결과

Acelere a inferência de LLMs usando especulative decoding, múltiplas cabeças Medusa e técnicas de lookahead decoding. Use ao otimizar velocidade de inferência (aceleração de 1,5-3,6×), reduzir latência em aplicações em tempo real ou fazer deploy de modelos com recursos computacionais limitados. Cobre modelos draft, atenção em árvore, iteração de Jacobi, geração paralela de tokens e estratégias de deploy em produção.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guide for the weight lifecycle — downloading trained weights from Tinker, merging LoRA adapters into HuggingFace models, and publishing to HuggingFace Hub. Use when the user asks about exporting, downloading, merging, or publishing trained model weights.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

병합 전 코드 변경을 기준 브랜치와 비교합니다. SQL 안전성, 대규모 언어 모델 입력의 신뢰 범위, 조건 분기의 부작용 등 구조적 문제를 점검합니다.

• 병합 전에 PR을 검토할 때
• SQL 변경의 안전성을 점검할 때
• 인공지능 입력의 신뢰 범위를 확인할 때

Review code changes from three critical perspectives: production failures, maintainability, and security. Get a consolidated report that ranks findings by severity and provides merge guidance, helping examine assumptions that an ordinary self-review may overlook.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a pull request before merging
• Getting a second opinion on AI-written code
• Checking authentication or data access code

Adapt large language models to specific tasks using LoRA and QLoRA, methods that train a small set of added parameters. Get guidance on preparing examples, choosing training settings, evaluating outputs, and saving or merging trained adapters.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adapting models to specialized terminology and output formats
• Planning training with limited GPU memory
• Preparing instruction-response datasets

Review code changes with an independent agent from a different model provider. After tests pass, check a fixed diff against acceptance criteria, send blocking issues back to the implementer, and repeat until review passes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Get an independent review from another model provider
• Check a pull request against acceptance criteria
• Turn blocking findings into concrete fix tasks

Estenda janelas de contexto de modelos transformer usando RoPE, YaRN, ALiBi e técnicas de interpolação de posição. Use ao processar documentos longos (32k-128k+ tokens), estender modelos pré-treinados além dos limites de contexto originais ou implementar codificações posicionais eficientes. Cobre embeddings rotativos, vieses de atenção, métodos de interpolação e estratégias de extrapolação para LLMs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Knowledge base synthesized from the Guide to the Systems Engineering Body of Knowledge (SEBoK) v2.14 by the BKCASE Project. Use for the established systems-engineering canon: SE fundamentals and foundations (systems science, systems thinking, the systems approach, modelling/MBSE), the life cycle (ISO/IEC/IEEE 15288/24748/24774 process, development & agile approaches, model selection/tailoring), technical management, concept definition, architecture/realization (the Vee), V&V, maintenance/sustainment, SE standards, and the application contexts (product, service, enterprise, systems-of-systems, healthcare), plus enabling SE (business/team/individual), related disciplines, quality attributes/specialty engineering, implementation examples, and emerging knowledge. Good for grounding background, vocabulary, and prior-art positions across all eight SEBoK Parts. SCOPE LIMITS: this pack is SEBoK v2.14 only (released 2026-05-18); it synthesizes and signposts rather than reproducing the source — it does not reproduce ISO/IEC/IEEE standard text, is a curated guide (not a complete textbook), and is thin on AI-integration depth (Part 8 is a staging area, not settled practice). LICENCE: content is CC BY-NC-SA 3.0 — non-commercial use only, attribution to the BKCASE Project required, share-alike obligations carry forward.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Review code changes in a diff, pull request, branch, or file path to identify bugs and cleanup opportunities. Findings include file locations and concrete failure scenarios, with options to apply fixes or post comments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review uncommitted changes for bugs
• Check a pull request or branch before merging
• Find duplicated logic and unnecessary work

Learn Apache Beam's core concepts through Java and Python examples. Understand distributed datasets, processing steps, pipeline execution, and time windows, with guidance on aggregation, late data, error handling, and sharing processing steps across languages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn how Pipeline, PCollection, and PTransform fit together
• Understand grouping, aggregation, merging, and splitting
• Study time windows, output timing, and late data

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Performs retrosynthetic planning using AiZynthFinder (template-based MCTS), maintained or version-pinned template-free models, ASKCOS, and emerging RetroSynFormer with explicit handling of route scoring, configurable MCTS rewards, building-block availability, and forward-prediction checks. Use when assessing synthetic feasibility of generated or selected molecules, planning multi-step syntheses, building synthesis-aware design pipelines, or screening libraries for retro-route feasibility.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when generating or editing images with Reve models on Scenario via MCP: text-to-image from a prompt alone, instruction edits (swap poster text, recolor a product, change materials, relight or restyle a scene), merging references with consistent subjects, blending up to 6 images into one composite, or choosing between Reve v2.1 and Reve Remix. Keywords: Reve v2.1, Reve Remix, Reve AI, txt2img, img2img, frame tags, compositing, style blending, text swap.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

On-demand procedures for the ComfyUI sidebar panel agent that are too long to sit in the system prompt. Read it when a task lands in one of these areas. subgraph boundary rails and blueprint reuse, merging or composing workflows across tabs, pinning your edits to one workflow, opening staged or downloaded workflow files, untangling Get/Set-bus and rgthree toggle-heavy graphs, authoring rgthree Fast Groups nodes, the LoRA Manager autocomplete-node limitation, the CivitAI browser flow, downloading model weights, reading hardware and runtime stats, Prompt Director audits, custom-node crash recovery, run-to-node render debugging, and multi-stage pipeline chaining. Each section is a lookup, not background reading. Reach for the one you need instead of guessing, and follow the tool's own description for parameter detail.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface: 6 tools with --full (adds check_action); 13 tools with AR_EXTRAS=1 --full. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Automatically simplify and minimize TLA+ specifications by reducing redundant state variables, merging equivalent actions, and minimizing invariants while preserving specified properties. Use when working with TLA+ specifications that need optimization, simplification, or reduction. Triggers when users ask to minimize, reduce, simplify, or optimize TLA+ specs, or when they want to remove redundancy from formal specifications while maintaining semantic equivalence.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Azure Document Intelligence REST SDK for TypeScript workflow skill. Use this skill when the user needs Extract text, tables, and structured data from documents using prebuilt and custom models and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Azure Document Intelligence REST SDK for TypeScript workflow skill. Use this skill when the user needs Extract text, tables, and structured data from documents using prebuilt and custom models and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Azure.AI.DocumentIntelligence (.NET) workflow skill. Use this skill when the user needs Azure AI Document Intelligence SDK for .NET. Extract text, tables, and structured data from documents using prebuilt and custom models and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Azure.AI.DocumentIntelligence (.NET) workflow skill. Use this skill when the user needs Azure AI Document Intelligence SDK for .NET. Extract text, tables, and structured data from documents using prebuilt and custom models and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Azure Machine Learning SDK v2 for Python workflow skill. Use this skill when the user needs Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Azure Machine Learning SDK v2 for Python workflow skill. Use this skill when the user needs Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AI.MD v4 — The Complete AI-Native Conversion System workflow skill. Use this skill when the user needs Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.