「dpo」の検索結果

Configures host-based intrusion detection systems (HIDS) to monitor endpoint file integrity, system calls, and configuration changes for security violations. Use when deploying OSSEC, Wazuh, or AIDE for endpoint monitoring, building file integrity monitoring (FIM) policies, or meeting compliance requirements for change detection. Activates for requests involving HIDS configuration, file integrity monitoring, OSSEC/Wazuh deployment, or host-based detection.

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。

Work safely with endpoint versions — preview a draft in the playground, roll back to an older version, update settings on one version without bumping query history, deactivate a specific version. Use when the user asks "how do I roll back my endpoint", "preview my changes before publishing", "I want to fix v5 without bumping the version", or anything involving the version history. Calls out today's limitations honestly: there is no pointer flip; "rollback" means forking the old query into a new top version.

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。

Build DPO training pipelines for AI alignment. TRIGGERS - Use when user needs help with ai-dpo-trainer related tasks.

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。

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

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。

Tests APIs for Broken Function Level Authorization (BFLA) vulnerabilities where regular users can invoke administrative functions or access privileged API endpoints by directly calling them. The tester identifies admin and privileged endpoints, then attempts to access them with regular user credentials by manipulating HTTP methods, URL paths, and request parameters. Maps to OWASP API5:2023 Broken Function Level Authorization. Activates for requests involving BFLA testing, admin endpoint bypass, function-level access control testing, or API privilege escalation.

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。

Configures host-based intrusion detection systems (HIDS) to monitor endpoint file integrity, system calls, and configuration changes for security violations. Use when deploying OSSEC, Wazuh, or AIDE for endpoint monitoring, building file integrity monitoring (FIM) policies, or meeting compliance requirements for change detection. Activates for requests involving HIDS configuration, file integrity monitoring, OSSEC/Wazuh deployment, or host-based detection.

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。

Responds to malware infections across enterprise endpoints by identifying the malware family, determining infection vectors, assessing spread, and executing eradication procedures. Covers the full lifecycle from detection through containment, analysis, removal, and recovery. Activates for requests involving malware response, malware eradication, trojan removal, worm containment, malware triage, or infected endpoint remediation.

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。

Build and deploy a paid API that other agents can pay to use via x402. Use when you or the user want to monetize an API, make money, earn money, offer a service, sell a service to other agents, charge for endpoints, create a paid endpoint, or set up a paid service. Covers "make money by offering an endpoint", "sell a service", "monetize your data", "create a paid API".

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。

Build FastAPI endpoints in the layered router → service → Supabase pattern, with Pydantic v2 schemas, JWT/admin gating, and consistent HTTPException-based domain errors. Use when adding/modifying any endpoint under backend/.

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。

Itôで予約済みのGPUを使ったモデル配信の相談に対し、現状の未対応範囲と将来必要な確認事項を整理するスキル。現在は配信を開始せず、制約を案内します。

• Itô GPU予約後の配信対応を確認したいとき
• OpenAI互換の接続先の制約を知りたいとき
• 将来のモデル配信設定を確認したいとき

Security-test a REST, GraphQL, or gRPC API with Strix — autonomous agents that enumerate endpoints from an OpenAPI/GraphQL schema (or by crawling), then actually exploit the API-specific vulnerability classes in the OWASP API Security Top 10 (2023) — broken object-level authorization (BOLA/IDOR), broken object property level authorization (excessive data exposure and mass assignment), broken function-level authorization, unrestricted resource consumption, SSRF, injection, and auth/token flaws. Every finding comes with a working proof-of-concept request. Use when the user asks to pentest, security-test, audit, or find vulnerabilities in an API, endpoint, or backend service.

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。

BFL FLUX API integration guide covering endpoints, async polling patterns, rate limiting, error handling, webhooks, and regional endpoints with Python and TypeScript code examples.

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。

为 Agent 模型做后训练或选路线时使用——判断该先补 Mid-training、用 SFT 立协议还是直接上 RL；构造 Mid-training 语料与 SFT 数据、搭建 RL 环境、在 GRPO/PPO/DPO 与蒸馏之间取舍；排查 pass@k 近零、格式不稳就训 RL、组内无奖励差异、训练-推理数值失配、过度训练泛化下降。触发词：后训练、Mid-training、继续预训练、SFT、RL、GRPO、PPO、DPO、拒绝采样、RFT、蒸馏、on-policy、RLVR、LoRA。

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。

Supports multivariate severity assessment and exploratory endpoint-time score forecasting for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast forecasting. Use when combining welfare readouts — body weight or weight loss, body temperature, clinical or nesting scores, biomarkers, activity, heart rate, burrowing, wheel running — into one severity score per animal per day, when asking which animals are at risk of reaching a humane endpoint at a specified future observation time, when defining attention/danger zones or thresholds on a severity scale by kernel density estimation, or when reporting severity for a 3Rs, refinement, animal-welfare, or EU Directive 2010/63/EU severity-assessment context. Covers directionality ("turned" variables), baseline normalization, reference sets, RELSA weights, ARIMA prediction intervals, and RMSE/PICP/MPIW 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。

Builds production-ready REST API endpoints with validation, error handling, authentication, and documentation. Follows best practices for security and scalability.

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。

Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosing between preference-optimization methods, or when a DPO run needs hyperparameters or debugging.

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。

Discover and inventory shadow API endpoints that operate outside documented OpenAPI/Swagger specs, using traffic analysis against API gateways (Kong, AWS API Gateway, Envoy), cloud configuration scanning, and source code repository mining for undocumented routes. Use when assessing API attack surface, auditing for forgotten test environments or deprecated API versions still running, or building an API registration governance policy.

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。

Detect Living Off the Land Binaries (LOLBins/LOLBAS) abuse including certutil, regsvr32, mshta, and rundll32 via process telemetry, Sigma rules, and parent-child process analysis with Sysmon endpoint data. Use when hunting for adversaries abusing built-in Windows binaries to download, execute, or proxy malicious code while evading traditional executable-based detection.

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。

Detects fileless malware and in-memory attacks that execute entirely in RAM without writing persistent files to disk, evading traditional antivirus. Use when building detections for PowerShell-based attacks, reflective DLL injection, WMI persistence, and registry-resident malware. Activates for requests involving fileless malware detection, in-memory attacks, PowerShell exploitation, or living-off-the-land techniques.

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。

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

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。

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.

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。

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

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。

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations.

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。

Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth model (user token / API key / global key), adding API endpoints, and the rule that API changes must update the MCP server and skills. Triggers on "langbot backend", "langbot dev", "langbot api", "add langbot endpoint", "langbot migration".

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。