85건 · 관련도순
Fornece orientação para pós-treinamento de LLM com RL usando slime, um framework Megatron+SGLang. Use ao treinar modelos GLM, implementar fluxos de trabalho personalizados de geração de dados, ou precisar de integração estreita com Megatron-LM para escalabilidade em RL.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Fetch up-to-date, version-specific documentation for any major library (Next.js 16, Sanity, LangGraph, React, Tailwind CSS, Vitest, Framer Motion) via the Context7 MCP server. Use when writing code against unfamiliar or recently-changed framework APIs, when training data may be stale, when resolving deprecations or version-specific syntax, or when the repo warns about framework drift (e.g. the nextjs-agent-rules block in portfolio-v1/AGENTS.md). Invokes the resolve-library-id and get-library-docs MCP tools.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Find current documentation and code examples through the Context7 MCP server. Look up library setup, API usage, migration steps, and library-specific problems, using documentation for the requested version when available.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Prepare an evaluation framework before fine-tuning a language model. Build labeled examples, checks for each failure type, and a base-model benchmark, while calibrating model-based judges against human labels to support comparisons after training.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Build image captioning, visual question answering, and text-based image search with BLIP-2. The skill explains model selection, batch processing, and memory-saving settings, with Python examples for connecting image understanding to language models.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Assess security risks in AI systems by scanning prompts for known attack patterns and scoring data exposure, poisoning, and tool abuse risks. Map findings to MITRE ATLAS, an AI threat framework, and identify protective controls.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job export; use when the user names plain PyTorch or preliminary source inspection identifies one plain-PyTorch owner, and not for Lightning, other frameworks, deployment, POC/production lifecycle, or experiment workflows.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
An overview of the core model API of SeisBench, a Python framework for training and applying machine learning algorithms to seismic data. It is useful for annotating waveforms using pretrained SOTA ML models, for tasks like phase picking, earthquake detection, waveform denoising and depth estimation. For any waveform, you can manipulate it into an obspy stream object and it will work seamlessly with seisbench models.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when asked 兴趣班怎么选, 孩子报几个兴趣班合适, 课外班规划, 双减后还能报什么班, 寒暑假怎么安排, 预付费培训退费, or plan a child's out-of-school activities in mainland China. Produces a weekly timetable that protects sleep, homework and free play, a choice framework (the child's interest, purpose, cost, travel), a term budget, a check of each class against the 双减 rules on academic training and prepaid fees, contract questions to ask a provider, and a review point to drop what is not working, with rules marked to confirm locally.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Framework for demonstrating AI capabilities in legal contexts. Provides detailed personas across tenant law, business contracts, startup disputes, employment claims, and consumer protection with progressive complexity scenarios. Use when: (1) Demonstrating AI-powered legal triage or intake systems, (2) Showcasing responsible AI-assisted client interactions, (3) Training staff on appropriate AI use in legal contexts, (4) Creating realistic scenarios for legal tech presentations, (5) Developing educational materials about AI in legal services, or (6) Testing AI-powered legal information systems in controlled environments.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents with tracing, configuring LightningStore, implementing reward functions, or optimizing prompts with RL/APO algorithms.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Searches current documentation, release notes, API references and public repository issues for libraries, frameworks, SDKs, APIs and CLI tools with `firecrawl developer`. Use before answering when the user names a version, is upgrading, pastes an error from a library or tool, or asks how to use, configure or migrate a specific library or API. Model knowledge stops at a training cutoff and misses new releases, renamed APIs, changed defaults and recent fixes, so when a version, option, error or API is unfamiliar or may have changed, look it up instead of guessing. Also checks whether a bug was fixed and in which release. Not for general programming concepts, code that uses no specific library, or refactoring code the user supplied.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Medical image segmentation with nnU-Net's self-configuring framework — auto-selects architecture, preprocessing, training for any modality. CT, MRI, microscopy, ultrasound in 2D, 3D full-res, 3D low-res, cascade. Pipeline: convert → plan/preprocess → train (5-fold CV) → best config → predict → ensemble. Use when classical segmentation fails and annotated data exists.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Routes substantive ML, AI, data, scientific-computing, and software-engineering requests to the smallest useful set of managed repository skills. Invoke proactively when a request names or implies a package, framework, model family, dataset, modality, workflow, backend, deployment target, evaluation method, or implementation approach that may benefit from repository guidance, even if no repository is named. Narrow progressively from area to family to repository root: inspect only the one or two most likely area pages; compare candidates by capability, task surface, model/data format, training versus inference versus evaluation intent, runtime constraints, and root-skill description; then open only the selected root and relevant sub-skills, references, or scripts. Select multiple repositories only when each adds a distinct capability. Do not load the whole collection, treat dependencies or incidental integrations as capabilities, choose by name alone, or force a match when no exact taxonomy family applies.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
TRIGGER THIS when preparing interviews, planning hiring processes, creating interview questions, building evaluation frameworks, developing interviewer guides, or standardizing interview approaches. Builds complete interview kits with competency-based questions, scorecards, rubrics, interviewer training, and structured evaluation protocols.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Context7 fetches current, version-specific documentation and code examples for software libraries and hands them to an AI coding agent, so generated code matches the library version in use instead of stale training data. Use when someone says "use context7", "get the latest docs for this library", "look up the current API", "the agent keeps using a deprecated method", "set up Context7 in Claude Code or Cursor", or asks how to call a framework whose API changed recently. Covers the ctx7 CLI, the MCP server and its two tools, library IDs and version pinning, API keys and rate limits, and the REST API.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Searches current documentation, release notes, API references and public repository issues for libraries, frameworks, SDKs, APIs and CLI tools with `firecrawl developer`. Use before answering when the user names a version, is upgrading, pastes an error from a library or tool, or asks how to use, configure or migrate a specific library or API. Model knowledge stops at a training cutoff and misses new releases, renamed APIs, changed defaults and recent fixes, so when a version, option, error or API is unfamiliar or may have changed, look it up instead of guessing. Also checks whether a bug was fixed and in which release. Not for general programming concepts, code that uses no specific library, or refactoring code the user supplied.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert sales enablement strategist for building high-performing sales teams. Use when designing sales training programs, onboarding and ramp plans, sales playbooks, coaching frameworks, certification programs, or competitive intelligence distribution. Covers content strategy, tool adoption, performance measurement, and continuous learning systems. Use for building sales academies, creating enablement content, and optimizing sales productivity.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert customer onboarding guidance for accelerating time-to-value and ensuring successful implementations. Use when designing onboarding programs, creating kickoff frameworks, building implementation plans, or optimizing customer activation. Use for training delivery, go-live readiness, sales-to-CS handoffs, early warning detection, and tech-touch automation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Implement a generative diffusion model (DDPM or score-based) with noise scheduling, U-Net architecture, training loop, and sampling procedures including DDIM acceleration. Use when building a generative model for image, audio, or molecular synthesis; implementing DDPM from a research paper; adding a custom noise schedule or conditioning mechanism; replacing a GAN-based generator with a diffusion alternative; or prototyping before scaling with production frameworks like diffusers.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.