'distillation' 검색 결과

Applies the engineering and research philosophies of Jeff Dean, Chief Scientist at Google DeepMind and Google Research. Reach for this skill whenever you are designing large-scale distributed systems, optimizing latency and energy efficiency, or making architectural decisions about machine learning infrastructure. It should trigger automatically for topics involving hardware-ML co-design, model distillation, sparse activation, massively multi-task models, or scaling systems by 5x to 10x. Use this skill to evaluate system bottlenecks, transition from specialized to unified models, and optimize experimental velocity. Apply his mental models to avoid premature 100x scaling and to treat AI models as reasoning engines rather than memorization databases.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Adapts LLMs: SFT dataset loss masking, LoRA and QLoRA, full FT vs PEFT, distillation, pruning, tokenizer fragmentation. Use when fine-tuning or compressing a model.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Interactive demo: Generate pseudo-labels from a strong teacher model, build a cheap student function, and evaluate accuracy. Showcases pseudo-labeling and teacher-student distillation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

通用知识沉淀能力。用于从 devflow 或其他交付过程的需求、设计、实现、审查、测试产物中提炼可复用经验、技术决策、踩坑记录和流程改进。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

通用知识沉淀能力 - 提供从项目交付过程中提炼可复用经验、教训和模式的标准化方法论，包括信息收集、精简提炼、结构化输出。不绑定任何特定工作流或存储方式。当用户说"帮我做知识沉淀"、"总结一下这次需求的经验"、"记录一下踩坑"、"沉淀一下这次的技术决策"、"做个复盘"时使用本技能。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Distill books, documents, folders, or URLs into compact, practical Agent Skills. Use when source material should become either one reusable skill package or a split set of focused skills, each with a concise SKILL.md plus detailed references and examples.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Distill books, documents, folders, or URLs into compact, practical Agent Skills. Use when source material should become either one reusable skill package or a split set of focused skills, each with a concise SKILL.md plus detailed references and examples.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Distill large models into smaller ones — teacher-student training, data generation, loss design, and quality validation. Use when you need big-model behavior at small-model cost.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generates structured case briefs from judicial opinions. Use when the user provides a court opinion and needs a case brief, case summary, or distillation of a judicial decision for legal research.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Adaptive learning for moflo agents via ReasoningBank: trajectory storage, verdict judgment, memory distillation, consolidation, and MMR retrieval. Use when building agents that should improve from experience across runs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert-level mass transfer covering molecular diffusion, convective mass transfer, interphase transfer, mass transfer coefficients, and design of mass transfer equipment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Post-train LLMs with PrimeIntellect's prime-rl (async RL, SFT, distillation, evals). Use this skill whenever the user mentions prime-rl, wants to write an rl.toml or sft.toml, run `uv run rl` / `uv run sft` / `uv run eval` / `uv run inference`, pick GRPO, MaxRL, OPD or ECHO, tune IPO loss, or monitor and resume a run. Also trigger for verifiers environments, Prime Intellect post-training, reverse-text, and pydantic-config TOML overrides.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Health-check the second brain so failures are not silent: is the local search server alive, is the RAG index fresh, is the session-memory ledger filling, did the nightly distillation run. Read-only, with a green/red verdict per component. Triggers: "/brain", "/memory", "is the reindex alive".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when turning expert materials, execution traces, repository evidence, or long-form documents into an inspectable, correctable, and empirically verified agent skill. Covers source governance, capability-vs-behavior separation, contrastive induction from successes and failures, intervention testing, versioning, rollback, and task-conditioned vs. reusable-library evaluation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

The paper 'When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation' revea

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Distills enduring architectural decisions and design rationale from wave orchestration plans or historical git changes into structured, tracked Architecture Decision Records (ADRs). Use pre-wave to resolve active architectural constraints or post-wave to record enduring decisions in docs/decisions/.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Incrementally studies git history across tagged or pattern-matched intervals (e.g., creation of planning artifacts like EXECUTION_PLAN_N.md, release tags, or milestone commits). Extracts commit diffs, file churn, and subsystem shifts to track feature evolution and architectural convergence, providing structured feeds for ADR distillation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OpenAI API (developers.openai.com) の Evals / Fine-tuning リファレンス。 Evals API, Datasets, graders（string check / text similarity / model / python / multi）, agent evals, trace grading, external models, Promptfoo（移行先）, red teaming, SFT, DPO, RFT, vision fine-tuning, distillation, prompt optimizer, fine-tuning best practices。 Evals は 2026-11-30 停止予定、セルフサービス fine-tuning は段階的廃止中。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Conduct Critical Decision Method (CDM) interviews to elicit expert reasoning strategies (L3 knowledge) from practitioners about specific challenging past incidents. Use when capturing expertise for skill development, preserving knowledge before practitioner departure, building post-incident learning artifacts, or investigating decisions in complex sociotechnical systems. Outputs structured incident reconstructions with cues, decisions, alternatives considered, and counterfactual analysis suitable for distillation into skills or training material.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Trial protocol for teaching AI Matrx an expert's knowledge until the platform breaks, fixing it. Use when asked to run an expertise trial, distil a person/creator/recent video into a Masterwork, or test the capture product. NOT for a known-missing feature (use build-sub-feature).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.