'nsf' 검색 결과

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

Helps extend how much text a language model can process at once. Covers choosing RoPE, YaRN, ALiBi, or position interpolation, implementing position information, fine-tuning on longer documents, and managing memory during inference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extend an existing model to handle longer documents
• Compare context extension methods
• Implement position information in attention layers

Guide knowledge distillation, where a smaller language model learns from a larger teacher. Covers training from teacher responses or prediction scores, adjusting training settings, and comparing outputs to support model compression and specialized training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compressing a large language model into a smaller model
• Training a specialized model from teacher-generated examples
• Comparing distillation methods and training settings

Helps reduce GPU memory use by loading large language models in 4-bit or 8-bit formats, a technique called quantization. Covers bitsandbytes configuration, memory checks, QLoRA fine-tuning, and training with memory-saving optimizers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Load a larger model within available GPU memory
• Compare 4-bit and 8-bit quantization settings
• Fine-tune a quantized model with QLoRA

Implement and troubleshoot large-model training with DeepSpeed across multiple GPUs. The skill covers memory optimization, parallel training, and numerical precision choices, alongside examples for storage transfers and models that divide work among specialized components.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review settings for distributed model training
• Tune transfers between NVMe storage and tensors
• Configure training with specialized model components

Use SAELens to train and analyze sparse autoencoders, which break model activations into a small set of interpretable features. Explore pretrained features, evaluate reconstruction quality, troubleshoot training, and test how individual features influence generated text.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exploring features in a pretrained SAE
• Training an SAE for a selected model layer
• Investigating inactive features and reconstruction errors

Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

Build Apache Spark pipelines for large datasets, including transformations, aggregations, and streaming analysis. Get PySpark or Scala code, partitioning strategies for dividing data across workers, and configuration advice to investigate slow jobs and resource usage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a pipeline to transform and aggregate large datasets
• Investigate slow Spark jobs and uneven data distribution
• Tune memory settings and data partitions

Build JavaScript or TypeScript applications that run text, image, and audio models in browsers or server runtimes. Guides compatible model selection, GPU or CPU execution, caching, and memory cleanup without requiring a Python server.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add text classification or translation to a browser app
• Implement image classification and object detection
• Transcribe audio using JavaScript

Plan an agent's handover to a fresh successor before its context fills up. Prepare transfer materials, preserve the role's address, record tenure history, and explicitly transfer recurring duties and authority while keeping a way to consult retained predecessors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a handover before an agent's context fills up
• Transferring recurring duties and authority
• Recording an agent role's tenure history

Review token contracts and the protocols that accept them for ERC20/ERC721 compliance, privileged controls, and unusual transfer behavior. Produces evidence-based risk assessments and prioritized fixes, with supply and holder analysis when deployed contract details are provided.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking ERC20/ERC721 implementations against their standards
• Reviewing support for tokens with unusual transfer behavior
• Assessing administrator powers and upgrade risks

Prepare 3D models for browser games by cleaning source assets, exporting GLB or glTF, and optimizing geometry and textures. It also guides collision shapes, distance-based detail levels, and runtime checks for the chosen engine.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing Blender models for browser games
• Reducing GLB or glTF asset size
• Planning collision shapes and distance-based model detail

Create and operate Starknet wallets for AI agents. Check token balances, send transfers, interact with smart contracts, and manage session keys, temporary permissions that let an agent perform approved transactions within spending limits and an expiry time.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a Starknet account for an AI agent
• Check balances across multiple tokens
• Send tokens and interact with contracts

Build JavaScript or TypeScript apps that interact with NEAR. This skill guides token transfers, smart contract calls, account and key management, transaction signing, and message authentication through near-api-js v7 examples.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding NEAR and token transfers to an app
• Reading and updating smart contract data
• Managing account keys and access permissions

Connect an AI agent to BNB Chain through MCP, a protocol for accessing external tools. Configure the server, inspect balances and transactions, transfer tokens, interact with contracts, register agents, and manage Greenfield storage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configure a connection to the BNB Chain MCP server
• Look up balances, blocks, and transactions
• Transfer tokens or interact with contracts

Write JavaScript for n8n Code nodes to aggregate, filter, and transform workflow data. Guidance covers data access, output formats, execution modes, common errors, and performance choices when processing large numbers of records.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Aggregating and deduplicating multiple records
• Transforming complex API responses
• Fixing data access and return format errors

Build n8n workflows that download, transform, and send files without losing their contents. Learn how file data differs from JSON, how to preserve attachments, and how to use storage keys or URLs with AI tools and chat messages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fixing attachments lost during data transformation
• Passing uploaded files to AI agent tools
• Displaying generated images in chat

Review and fix how MSBuild manages lists of files and their metadata, or attached information. Check Include, Remove, Update, filtering, path transformations, duplicates, and execution grouping to clarify whether item operations behave as intended.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing Include, Remove, and Update usage
• Investigating duplicate or overlapping file entries
• Checking metadata-based execution grouping

Compare original and rewritten academic text to check that citations, statistics, and core claims remain intact. Receive a report covering writing quality, scholarly tone, and whether the changes should be approved, reviewed, or rejected.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check citations after rewriting academic text
• Compare statistical values before and after editing
• Review changes to claims and conclusions

Refine AI-assisted academic drafts into natural scholarly prose while preserving citations, statistics, and methodological details. Choose how extensively to revise and which sections to edit, then review a report comparing the original and revised text.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Polishing an AI-assisted academic draft
• Making minimal edits before journal submission
• Revising only the abstract and discussion

Review a grant proposal before submission through six specialized perspectives. Receive a consolidated report covering funder fit, research methods, feasibility, budget, consistency, and writing, with prioritized revisions and questions a review panel might ask.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a grant proposal before submission
• Checking alignment with a target funder
• Finding gaps across methods, budget, and timeline

Prepare survey and administrative datasets for analysis with Python, R, or Stata. Generate cleaning code to handle missing values, duplicates, outliers, and derived variables, with documented transformations and integrity checks that support reproducible research.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clean missing values, duplicates, and outliers in survey data
• Merge multiple data sources for analysis
• Prepare panel datasets that track units over time

Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train agents from historical experience
• Build decision-making for games and navigation
• Combine experience from multiple agents for training

Create and install Observal Agents, edit their definitions, and manage publication and version releases. The skill also supports forking approved Agents, archiving and restoring them, transferring ownership, and managing co-authors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create and publish an Agent
• Install an existing Agent
• Customize an approved Agent