'without' 검색 결과

Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running GPU inference without managing servers
• Deploying a model as an automatically scaling API
• Processing large batches in parallel

Build image classification and search workflows by comparing images with text descriptions. Covers classification without additional training, similarity scoring, batch processing, and storing image representations in a vector database for retrieval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classifying images without additional training
• Searching image collections with text descriptions
• Comparing images with candidate descriptions

Reduce LLM weight usage through pruning, which removes selected model parameters. Explore Wanda and SparseGPT for compression without retraining, choose hardware-friendly patterns for faster inference, and compare the compressed model's accuracy with the original.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compressing an LLM without retraining
• Comparing pruning methods
• Exploring faster inference on supported hardware

Convert attached office documents, EPUB, CSV, and text-based PDFs into local Markdown using Firecrawl AnyDoc CLI. Files stay inside the agent container, producing readable text for review without uploading documents to an external parsing service.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Read an attached Word document as Markdown
• Extract reading context from spreadsheets or CSV files
• Convert presentations or EPUB files for text review

Add Tavily web search and URL content extraction to selected NanoClaw agent groups without an API key. Configures MCP, a protocol for connecting agent tools, checks availability, and prepares an upgrade path when the shared allowance runs out.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add web search to selected agent groups
• Extract structured information from URLs
• Start using Tavily without an API key

Equip NanoClaw agents to convert attached office documents into Markdown locally using Firecrawl AnyDoc. Agents can read Word, PowerPoint, Excel, and text-based PDF files without uploading them to an external parsing service.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reading and summarizing attached office documents
• Converting documents without uploading them to an external service
• Extracting text from text-based PDFs

Scope a Claude Managed Agent through six questions about its job, trigger, inputs, actions, success criteria, and recurrence. Produce a validated build sheet with configuration components, deferred features, and an evaluation plan, without requiring an API key.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn an agent idea into a concrete build plan
• Define success criteria before implementation
• Separate the initial scope from later integrations

Automate browsing in cmux panels without taking focus away from current work. Target a specific panel to open pages, fill forms, click controls, wait for page changes, extract content, and inspect download history.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Open and inspect sites without changing focus
• Fill forms and check the result
• Extract page text or HTML

Guides image classification and search with OpenAI's CLIP by comparing images with text descriptions, without additional training. Includes batch processing, image-text matching, and category-based checks for potentially inappropriate images.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classify images using text labels without additional training
• Search an image collection with natural-language descriptions
• Compare how closely images match text descriptions

Guides LLM compression through pruning, which removes selected model weights. Covers Wanda and SparseGPT methods without retraining, accuracy comparisons, and structured weight patterns that can accelerate inference on compatible hardware.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trying model compression without retraining
• Comparing accuracy before and after pruning
• Choosing between Wanda and SparseGPT

Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running GPU inference without managing servers
• Deploying a model as an automatically scaling API
• Processing large batches in parallel

Build Vue 3 applications using JavaScript and JSDoc comments that describe data types. Create components and reusable logic, configure Vite, routing, and state management, and check annotations and behavior with ESLint and Vitest.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build Vue 3 interfaces using JavaScript
• Add JSDoc type hints to components and shared logic
• Migrate Vue 2 Options API code to Composition API

Train or fine-tune language and vision models on Hugging Face Jobs without a local GPU. Covers dataset checks, hardware and cost planning, training monitoring, Hub storage, and GGUF conversion for local use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tune a language model without a local GPU
• Validate preference data before DPO training
• Estimate training costs and choose GPU hardware

Verify Claude Agent SDK build and release scripts without network access. Run command-line workflows in an isolated environment with substitute commands to check version validation, installer handling, and retries without overwriting the developer’s installed Claude binary.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check accepted and rejected CLI version values
• Confirm wheel builds reject invalid version pins early
• Test download failures and retry behavior

Guide changes to OpenRig itself by locating relevant source files, choosing tests, assessing sensitive areas, and preparing pull requests. Use isolated test environments to check changes without disrupting the daemon running the current agent session.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Locate the source files responsible for a behavior
• Choose tests for an OpenRig change
• Test without disrupting the current agent session

Check harness changes on a host without Docker by running the pinned Claude Code CLI against a local mock API server. Capture request headers and verify behavior using the authentication environment generated by the harness.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check authentication changes without Docker
• Inspect headers sent by the real CLI
• Reproduce the environment passed to container agents

Open the Creative Production start screen when a creative request is still undefined. The app presents starter choices that lead to an editable prompt, providing an entry point before a concrete production request is submitted.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Opening Creative Production without a detailed brief
• Exploring starter choices before deciding what to make
• Drafting a request from an editable starter prompt

Make specific C# behavior testable by adding a minimal way to replace time, randomness, or other external dependencies. Preserve public APIs and production behavior, then run repeatable tests without real file access or waiting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing deadlines and delays with controlled time
• Testing file operations without touching real files
• Testing random or environment-dependent behavior

Install a .NET SDK, the tools used to build .NET projects, inside a project folder. Configure version selection and shared setup scripts to test previews or reproduce team and CI environments without changing the system installation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trying a .NET preview without changing the system installation
• Pinning a project to a specific SDK version
• Creating repeatable setup scripts for teams and CI

Review multi-factor authentication flows for skipped checks, reused one-time codes, weak backup paths, and verification races. It focuses on proving access to protected resources rather than relying on interface behavior or response codes alone.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check access before completing multi-factor authentication
• Test one-time code reuse and validation behavior
• Review backup codes and trusted-device cookies

Audit writing for repetitive phrases, vague praise, excessive formatting, and other patterns associated with AI text. Get a revised version with reasons for changes, or use detection mode to review flagged passages without altering the original.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Edit repetitive phrasing in an AI-generated draft
• Flag patterns without changing published text
• Reduce excessive emphasis and bullet lists

Collect user-provided API keys and other credentials through a form and save them to a specified dotenv configuration file. Request multiple variables together without exposing their values in chat, command arguments, or output visible to the agent.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configure API keys in .env.local
• Request several credentials in one form
• Update credentials without sharing values in chat

Select open pull requests for initial classification and distribute them to dedicated workers with a concurrency limit. Record why each request is included or excluded, without merging changes, assigning owners, or requesting reviewers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classify a mixed list of open pull requests
• Include community pull requests without linked issues
• Limit concurrent triage workers

Connect an existing socket application to a BlueField DPU without rewriting the application. This skill guides relay placement, endpoint configuration, a single-client round-trip check, and diagnosis of refused connections or traffic that stops flowing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connecting an existing socket application to BlueField
• Choosing between process, sidecar, and container deployment
• Diagnosing refused connections or missing data