'mode' 검색 결과

Add a diffusion model or Diffusers generation pipeline to SGLang. Examine reference code, choose a suitable pipeline structure, reuse existing components, and implement model settings and processing stages, with guidance for later multi-GPU support.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a new diffusion model to SGLang
• Porting a Diffusers generation pipeline
• Adding a variant by reusing existing model components

Integrate a model or pipeline into diffusers, from file structure and weight conversion to tests and documentation. Verify numerical agreement with the original implementation, with modular pipelines as the preferred starting point for new integrations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a new model and pipeline to diffusers
• Converting a pipeline to modular format
• Converting weights for a new version of a supported model

Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting company or profile details into JSON
• Classifying text using a fixed set of labels
• Generating text that matches a specified pattern

Convert LLMs to GGUF and reduce model size through quantization, which stores weights at lower numerical precision. Prepare models for CPU or Apple Silicon inference, compare compression levels, and integrate them with local AI tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing an LLM for CPU-only use
• Running a local model on Apple Silicon
• Comparing model size and quality across quantization levels

Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a small model on Shakespeare using a CPU
• Prepare custom text for model training
• Further train a pretrained GPT-2 model

Reduce GPU memory use by loading language models in 8-bit or 4-bit formats with bitsandbytes and HuggingFace Transformers. Includes configuration examples, QLoRA fine-tuning of compressed models, and optimizers that reduce memory needed during training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Load larger models within limited GPU memory
• Compare 8-bit and 4-bit model settings
• Fine-tune a model with QLoRA

Compress large language models to 4-bit weights to reduce GPU memory use and accelerate inference. Covers loading compressed models, configuring quantization, and using Transformers or vLLM, with guidance on hardware requirements and backend choices.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running large models with limited GPU memory
• Compressing a model with domain-specific sample text
• Serving AWQ models with vLLM

Build and train Mixture of Experts models, which activate selected specialist networks for each input. Use DeepSpeed or HuggingFace workflows to configure routing, balance workloads, distribute experts across GPUs, and optimize inference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing MoE models for a limited compute budget
• Implementing Mixtral-style expert routing
• Adjusting expert workloads and training stability

Create PowerPoint presentations centered on GLB 3D models, with rotation, zoom, and Morph transitions that smoothly connect slides. The skill also guides model selection, color palettes, typography, and layouts that support the presentation’s subject.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Presenting a product from several angles
• Explaining structures with a 3D model
• Finding a model that matches a presentation topic

Create a Google Model Armor template for checking AI prompts and responses. Specify a Google Cloud project, location, and template ID, then use a preset or provide custom settings in JSON.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a template with the jailbreak preset
• Defining template settings in JSON
• Preparing a template for prompt and response checks

Coordinate multiple agents to maintain context-mode, from sorting GitHub issues and reviewing pull requests to preparing releases and announcements. Workflows require reproduced bugs, source evidence, test-first changes, and checks across supported platforms.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating reported bugs and their history
• Reviewing contributor pull requests
• Preparing releases and compatibility checks

Index local files or folders in context-mode’s persistent search database, so later searches can retrieve relevant passages without rereading entire files. Useful for repeatedly consulting project documents while keeping raw file contents out of the conversation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing project documents for repeated searches
• Finding relevant passages in local files
• Indexing a repository with selected folders excluded

Open the hosted context-mode Insight dashboard in your default browser to access analytics for AI-assisted engineering teams, including productive rates per engineer, retry waste, blockers, and views tailored to different roles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Opening the team's development analytics dashboard
• Reviewing productive rates and retry waste per engineer
• Checking blockers and views tailored to team roles

Let a NanoClaw container agent call local models running in Atomic Chat. The skill adds an MCP server, a connection that exposes model listing and text generation as tools, while Claude continues to coordinate the work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Delegate part of Claude's work to a local model
• List models available in Atomic Chat
• Generate an answer with a specified local model

Switch a NanoClaw agent group to a local Ollama model by configuring environment variables and model settings. The skill covers setup checks, optional blocking of Anthropic API access, verification, troubleshooting, and switching back to Claude.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running a NanoClaw agent with a local model
• Reducing use of the Anthropic API
• Trying open-weight models through Ollama

Analyze a codebase to identify valuable assets, attack entry points, and realistic abuse paths. Produce a concise Markdown threat model that explains risk priorities, distinguishes existing protections from proposed mitigations, and makes assumptions explicit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Map attack entry points in a codebase
• Assess threats within a specific project directory
• Prioritize risks to sensitive data and credentials

Get source-backed guidance on OpenAI products, APIs, and Codex from official documentation. Use it to compare models for a task, understand configuration options, or plan focused model and prompt updates while preserving an explicitly requested target model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking OpenAI API usage and parameters
• Choosing an OpenAI model for a specific task
• Planning model upgrades and related prompt changes

Build, run, and debug the Kilo JetBrains plugin using its Gradle workflows. It covers isolated development storage, chat logs, sandbox recovery, and switching between a pinned CLI release and locally built CLI code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a versioned plugin ZIP for testing
• Run the plugin in a sandbox or split mode
• Inspect chat logs and session events

Test an idea, strategy, or investment against 11 future time horizons, from six months to 50 years. Compare scenarios with probability ranges, identify structural risks, and review or update the underlying world models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing an investment thesis across time horizons
• Reviewing long-term risks to a business model
• Updating future scenarios after major events

Analyze a codebase to identify valuable assets, attack entry points, and realistic abuse paths. Produce a concise Markdown threat model that explains risk priorities, distinguishes existing protections from proposed mitigations, and makes assumptions explicit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Map attack entry points in a codebase
• Assess threats within a specific project directory
• Prioritize risks to sensitive data and credentials

Check or configure how an Obsidian vault organizes knowledge, then suggest destinations for new notes using Generic, LYT, PARA, or Zettelkasten. Preview configuration changes before applying them; existing notes stay in place.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check the vault's current organization method
• Configure PARA or another supported method
• Find a destination for a planned concept note

Train Mixture of Experts models, which activate selected specialist networks for each input. The skill guides architecture, input routing, workload balancing, and GPU distribution using DeepSpeed or HuggingFace, with examples for training configuration and inference optimization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a model that activates only selected expert networks
• Balancing workloads across expert networks
• Distributing experts across multiple GPUs

Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting company or profile details into JSON
• Classifying text using a fixed set of labels
• Generating text that matches a specified pattern

Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a small model on Shakespeare using a CPU
• Prepare custom text for model training
• Further train a pretrained GPT-2 model