73건 · 관련도순
Set up and run supervised fine-tuning (SFT) on instruction or chat datasets using the Tinker API. Use when the user wants to do instruction tuning, chat fine-tuning, or supervised learning.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Prepare high-quality datasets for LLM fine-tuning with filtering, deduplication, augmentation, and RLHF data formatting. Activate on: fine-tuning data, training data curation, RLHF dataset, data quality filtering, SFT dataset. NOT for: model training infrastructure (ai-engineer), prompt engineering without fine-tuning (prompt-engineer).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
주식과 암호자산 가격을 조회하고 회사 이름으로 종목 코드를 찾습니다. Yahoo Finance 데이터로 과거 추이와 기간 등락률을 확인하고 여러 종목을 비교합니다.
Review stock analysis, technical backtests that simulate strategies on historical data, and saved research for selected tickers. Examine research dates, model details, risk factors, and simulation limits when reviewing a stock or watchlist.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Scan selected market symbols for unusual price movements and rank potential trading signals. Combine anomaly scores, measures of departure from normal behavior, with strategy filters, historical pattern matches, and predictions about changing market conditions.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn agent failure records into training examples by locating the first incorrect decision and pairing preferred actions with rejected ones. Assess whether training is appropriate, then check both targeted improvements and preservation of correct behavior.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Configure supervised fine-tuning for models that process images and text. Define which components remain unchanged, set LoRA adapters for updating selected model weights, choose image resolution limits, and investigate training runs whose evaluation results fail to improve.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Verify changes to Office add-in administration scripts using a temporary home directory. It covers syntax checks, cache-clearing behavior, identifier handling, and storage comparisons to check that removing add-in manifests preserves chat history.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Retrieve U.S. company filings and financial series from SEC EDGAR. Resolve stock tickers to company identifiers, list recent reports with document links, and fetch reported metrics such as revenue or assets without an API key.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Review companies before buying shares using six checks covering business clarity, financial strength, competitive advantages, management, valuation, and decision discipline. Get evidence-based reports, risk summaries, and comparison tables for multiple companies.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Connect stock data to an application using Finnhub Stock API. The skill covers current quotes, company profiles, historical prices, and market news, with server-side request handling to protect API keys and manage cached responses.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Research securities and listed companies across Chinese A-share, Hong Kong, US, and global markets. Retrieve price history, financial statements, filings, and news using scripts and browser checks, keeping source URLs, market identifiers, and reporting periods.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Assess Microsoft 365 and Entra ID authentication using tenant discovery, login error analysis, and browser-based verification. It provides attempt tracking and evidence templates to distinguish credential results from access-policy restrictions.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validation, and job export; use when the user names Hugging Face or preliminary source inspection identifies one Hugging Face owner, and not for manual PyTorch loops, Lightning, inference-only pipelines, deployment, or experiment workflows.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use when selecting a starting recipe, comparing library and benchmark configs, resizing parallelism for a GPU allocation, or distinguishing convergence changes, semantics-preserving execution tuning, and benchmark-only shortcuts.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
[omh] Fine-tuning a model on your own data -- SFT, DPO, RLVR or a LoRA adapter: decide first whether prompting or retrieval already closes the gap, choose the method from the data you have, and promote a checkpoint only when it beats the untuned baseline on a held-out eval. Use when the user says: model-finetuning, model finetuning, model fine-tuning, fine-tune a model, fine-tune the model, fine tune a model, fine tune the model, fine-tune.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Fetch financial and market data with the yfinance Python library (Yahoo Finance). Use this skill whenever the user wants stock data: current quotes and price history, financial statements (income statement, balance sheet, cash flow), options chains, dividends and splits, earnings and analyst estimates, price targets and ratings, institutional and insider holdings, news, multi-ticker comparisons, stock screens, or sector and industry data. Use it even when the user gives only a ticker symbol (AAPL, MSFT, TSLA) and the intent has to be inferred. For earnings previews or recaps, estimate revisions, valuation, correlation, liquidity, or ETF premium analysis, prefer the dedicated skill.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Selects, deploys, and customizes AI models on Amazon SageMaker. Training or Processing jobs, fine-tuning (SFT/DPO/RLVR/RLAIF), model selection, dataset preparation, evaluation, SageMaker or Bedrock deployment, inference optimization and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing which base model to customize, fine-tune, or deploy from SageMaker JumpStart or Hub, SageMakerPublicHub, or the SageMaker public model catalog, transforming or validating training data, evaluating model quality, deploying or optimizing endpoints, configuring IAM/S3 for training, or managing SageMaker Managed MLflow. Use for endpoint health, failures, latency, logs, metrics, errors. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reference for the TRL (Transformer Reinforcement Learning) library codebase. Use proactively before reading or editing any file under `trl/` so you have the intended contracts and invariants in mind, not just what the current code says. Covers trainer hierarchy (SFT, DPO, GRPO, KTO), shared utility functions (selective_log_softmax, decode_and_strip_padding, padding helpers), configuration system, model wrappers, and how data flows through any TRL trainer.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.