모든 Claude 스킬 탐색

LlamaGuard AI Content Moderation

Moderates LLM inputs and outputs using Meta's specialized LlamaGuard models to ensure safety and policy compliance across six critical categories.

GRPO RL Training Specialist

Implements Group Relative Policy Optimization (GRPO) for reasoning and task-specific model alignment using the TRL library.

TensorBoard ML Visualization

Visualizes machine learning training metrics, model architectures, and performance profiles using Google's TensorBoard toolkit.

AWQ LLM Quantization & Optimization

Optimizes Large Language Models using 4-bit activation-aware weight quantization to achieve 3x faster inference with minimal accuracy loss.

LM Evaluation Harness

Evaluates Large Language Models across 60+ academic benchmarks using standardized prompts and metrics for reproducible research.

Outlines Structured Generation

Ensures guaranteed valid JSON, XML, and type-safe code generation from LLMs using constrained token sampling and Pydantic models.

NeMo LLM Evaluator

Evaluates Large Language Models across 100+ industry-standard benchmarks using NVIDIA's enterprise-grade containerized architecture.

NeMo Curator Data Processing

Accelerates LLM data curation using GPU-powered deduplication, quality filtering, and PII redaction at scale.

TorchTitan LLM Pretraining

Accelerates large-scale LLM pretraining using PyTorch-native 4D parallelism and Float8 optimization.

GGUF Model Quantization

Optimizes large language models for efficient local inference using GGUF format and llama.cpp quantization techniques.

BigCode Evaluation Harness

Evaluates AI code generation models using industry-standard benchmarks and pass@k metrics.

OpenRLHF Model Training

Deploys and manages high-performance RLHF training pipelines for large-scale language models using Ray and vLLM acceleration.

DeepSpeed Distributed Training

Optimizes large-scale model training using DeepSpeed configurations, ZeRO optimization stages, and high-performance I/O management.

nnsight Remote Interpretability

Interprets and manipulates neural network internals across local and remote models using the nnsight library and NDIF execution.

LangSmith LLM Observability

Monitors, debugs, and evaluates large language model applications with comprehensive tracing and systematic testing tools.

NeMo Guardrails Safety Alignment

Implements programmable safety rails and runtime validation for LLM applications using NVIDIA's NeMo Guardrails framework.

Qdrant Vector Search

Manages high-performance vector similarity search and scalable storage for production RAG and semantic search systems.

LLM Quantization with bitsandbytes

Quantizes Large Language Models to 8-bit or 4-bit formats to reduce memory usage by up to 75% with minimal accuracy loss.

LitGPT LLM Implementation & Training

Implements, fine-tunes, and deploys high-performance Large Language Models using Lightning AI's LitGPT framework.

PyTorch FSDP2 Distributed Training

Implements advanced PyTorch FSDP2 sharding and distributed checkpointing for efficient large-scale model training.

Model Merging & Fusion

Combines multiple fine-tuned AI models into a single high-performance model without requiring additional training or expensive GPU resources.

RWKV Model Architecture

Implements and manages RWKV architectures for efficient, linear-time AI inference and long-context processing.

Lambda Labs GPU Cloud

Provisions and manages high-performance GPU infrastructure on Lambda Labs for machine learning training and inference workflows.

Modal Serverless GPU

Deploys and scales machine learning workloads on high-performance serverless GPUs using a Python-native framework.

HuggingFace Accelerate Distributed Training

Simplifies PyTorch distributed training across multiple GPUs, TPUs, and nodes with minimal code changes and a unified API.

MLflow MLOps Manager

Manage the complete machine learning lifecycle including experiment tracking, model versioning, and deployment using the MLflow framework.

Chroma Vector Database

Manages high-performance vector embeddings and metadata for RAG applications and semantic search using the open-source Chroma database.

GPTQ Model Quantization

Compresses large language models to 4-bit precision to enable high-speed inference and deployment on consumer-grade hardware.

Speculative Decoding & Inference Optimization

Accelerates LLM inference speed by up to 3.6x using speculative decoding, Medusa heads, and lookahead techniques without sacrificing model quality.

LLaMA-Factory Fine-Tuning

Streamlines the fine-tuning of 100+ large language models using LLaMA-Factory with support for QLoRA and multimodal architectures.