데이터·AI 스킬

Generate model responses in defined formats for data extraction and classification. Use JSON schemas, Pydantic data models, regular expressions, or fixed choices to produce structured results that other programs can parse and validate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting company or product details from text
• Classifying reviews into predefined labels
• Turning profile text into structured fields

Build question answering and document retrieval workflows with DSPy by defining inputs, outputs, and reusable components. Use training examples and evaluation metrics to automatically optimize prompts and compare results before and after optimization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building question answering with document retrieval
• Optimizing prompts using training examples
• Extracting structured information from text

Set up vLLM to serve large language models through an OpenAI-compatible API or process prompts in batches. The skill covers deployment, performance monitoring, and quantization, which reduces model memory requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploying an OpenAI-compatible language model API
• Generating text from large batches of prompts
• Serving large models with limited GPU memory

Find language models on Hugging Face Hub and run them locally with llama.cpp. The skill helps compare GGUF model files, choose compressed versions that fit available memory, and prepare commands for a local chat server or command-line session.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find a model that fits local RAM or GPU memory
• Compare available GGUF files and sizes
• Prepare a local chat server command

Use SAM to separate objects from images by marking points or drawing boxes, without training a model for each task. Covers automatic region generation, refining selections, preparing annotation data, and exporting models for deployment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extract an object with a transparent background
• Build an interactive image annotation tool
• Generate region masks for vision model training

Get guidance for fine-tuning large language models with Axolotl, adapting them through additional training. Use YAML configuration examples, dataset references, and training methods such as LoRA to set up training and investigate problems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing YAML configuration for model fine-tuning
• Exploring LoRA and QLoRA training methods
• Checking dataset formats and API usage

Use the hf command-line tool to find, download, and upload models and datasets on Hugging Face Hub. The guide also covers repository management, hosted computing resources, local cache maintenance, and automation options.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find and download models or datasets
• Upload local files to the Hub
• Create repositories and manage branches or tags

Helps you use Unsloth for language model fine-tuning with LoRA and QLoRA, methods that adapt models with fewer trainable parameters. Supports API questions, implementation, and debugging using reference material drawn from official documentation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning how to fine-tune models with LoRA or QLoRA
• Looking up Unsloth features and APIs
• Investigating errors in training code

Guide language model training with TRL using example answers, preferred response pairs, or reward scores. The skill covers data preparation, method selection, reward model training, evaluation, and adjustments for memory limits or unstable training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a language model to follow instructions using example answers
• Train on preferred and rejected responses with DPO
• Build a reward model and run an RLHF training pipeline

Set up large language model pretraining with TorchTitan and PyTorch. Configure training across multiple GPUs, combine four ways of splitting the workload, enable Float8 calculations on H100 hardware, and manage checkpoints for saving and resuming training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Pretraining Llama 3.1 8B on a single node
• Launching training across multiple nodes with SLURM
• Configuring Float8 training for H100 GPUs

Track machine learning experiments in W&B, record training settings and metrics, and compare results in dashboards. Automate searches for training settings and keep version histories for models and datasets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing accuracy across training runs
• Monitoring training progress in dashboards
• Searching for better training settings

Evaluate large language models on shared tests of knowledge, reasoning, and code generation with lm-evaluation-harness. Save scores and individual predictions, compare models in tables, and track performance across saved stages of model training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluating models on MMLU and GSM8K
• Building comparison tables for multiple models
• Tracking scores across training checkpoints

Extract website content using direct HTTP requests, JavaScript-capable browsers, or stealth browsing with Cloudflare handling. Use selectors to collect specific data, crawl linked pages, and export results as Markdown, text, HTML, or JSON.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extract text and links from static pages
• Collect content rendered by JavaScript
• Crawl multiple pages and save structured data

Set up and optimize large language model inference, or response generation, on NVIDIA GPUs. Use quantization, batch processing, and multiple GPUs to improve serving performance, and expose models through a chat completion API.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Serving a language model through a chat completion API
• Processing many prompts in batches
• Configuring quantization to reduce memory use

Improve prompts, regex patterns, SQL queries, or small code snippets through repeated scoring and revision. The skill helps define measurable tests, generate new candidates with an AI model, and inspect results to find better-performing versions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Improve a prompt against example answers
• Refine a regex using pass rates
• Improve SQL or code using tests

Build agent memory with Pinecone by storing searchable representations of conversations and documents. Retrieve relevant past context for answers, organize memory by session or user, and prototype semantic search that finds information by meaning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building agent memory that persists across sessions
• Adding retrieved context to agent answers
• Organizing memory separately for each user

Analyze and modify refusal behavior in open-weight language models without retraining. Use OBLITERATUS to select methods suited to available hardware, compare approaches, and evaluate changes in refusal rates and response quality.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Studying how language models produce refusals
• Testing refusal-related weight changes without retraining
• Selecting models and methods for available hardware

Explore concepts learned by language models using sparse autoencoders, which separate internal activity into a small set of features. Analyze pretrained models, train custom autoencoders, assess reconstruction quality, and experiment with feature based output adjustments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exploring features with a pretrained SAE
• Training an SAE for a chosen model layer
• Comparing feature responses across input texts

Find and run over 150 cloud AI apps through a shared command-line tool. Generate images and videos, search for information, or upload local images and audio for tasks such as upscaling and avatar generation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate images from prompts
• Turn a local image into a video
• Create an avatar video from a photo and audio

Build similarity search with Qdrant, a database for numerical representations of content. Store and retrieve vectors, filter results by metadata, connect retrieval to AI answers, and configure memory usage and deployment for larger workloads.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrieving reference documents for AI answers
• Filtering similarity search by category or date
• Building real-time recommendations

Set up reinforcement learning, training guided by response rewards, for large language models. Use Megatron-LM and SGLang to prepare data, configure training and response generation, and build asynchronous or multi-turn experiments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up GRPO training for a language model
• Overlapping response generation and training
• Training agents that use tools across multiple turns

Helps you build similarity search with FAISS to find nearby vectors, numerical representations of data. Covers index selection, saving and loading, GPU use, and tuning search speed, accuracy, and memory consumption for large datasets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building similarity search over large vector datasets
• Choosing indexes for speed, accuracy, and memory use
• Running batch searches on GPUs

Use LLaVA, a model that understands images and text, to answer questions about pictures, write image descriptions, and build image chat applications. Includes guidance for setup, ongoing conversations, and model memory options.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing descriptions for photographs
• Asking questions about objects and scenes
• Building a chatbot that discusses images

Integrate Flash Attention into Transformer models to speed up attention, the calculation that relates input elements, while reducing GPU memory use. Covers PyTorch integration, performance measurement, output comparison, and a separate H100 optimization path.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Optimize training with long input sequences
• Reduce memory use during long-context inference
• Measure speed and compare model outputs