모든 Claude 스킬 탐색

Mamba Architecture Guide

Implements and optimizes Selective State Space Models (SSM) for high-performance sequence modeling and long-context AI applications.

verl LLM Reinforcement Learning

Trains large language models using advanced reinforcement learning algorithms like GRPO and PPO with the production-ready verl framework.

Segment Anything Model (SAM)

Implements zero-shot image segmentation using Meta AI's SAM to identify and extract objects via points, boxes, or automatic mask generation.

FAISS Vector Search

Implements efficient similarity search and clustering for dense vectors at scale using Facebook AI's high-performance library.

Outlines Structured Generation

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

MLflow MLOps Manager

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

TensorBoard ML Visualization

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

OpenRLHF Model Training

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

Pyvene Causal Interventions

Facilitates causal interventions on PyTorch models using a declarative framework for mechanistic interpretability experiments.

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.

LM Evaluation Harness

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

ML Paper Writing for AI Research

Drafts publication-ready ML and AI research papers for top-tier conferences like NeurIPS and ICML directly from your research codebase.

HuggingFace Tokenizers

Provides high-performance, Rust-based tokenization tools for building and training NLP models with support for BPE, WordPiece, and Unigram algorithms.

PyTorch Lightning Training

Standardizes and accelerates PyTorch model training with built-in support for distributed computing, logging, and engineering best practices.

BLIP-2 Vision-Language

Implements state-of-the-art vision-language pre-training to enable high-quality image captioning and visual question answering within AI workflows.

TRL LLM Fine-Tuning & Alignment

Fine-tunes and aligns Large Language Models using Supervised Fine-Tuning and Reinforcement Learning from Human Feedback via the TRL library.

GGUF Model Quantization

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

AutoGPT Autonomous Agents

Builds, deploys, and manages continuous AI agents through a visual workflow builder or specialized development toolkit.

nnsight Remote Interpretability

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

GPTQ Model Quantization

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

LangChain Framework Integration

Builds sophisticated LLM applications using agents, chains, and Retrieval-Augmented Generation (RAG) with a unified interface.

AWQ LLM Quantization & Optimization

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

PEFT LLM Fine-Tuning

Optimizes large language model fine-tuning using LoRA, QLoRA, and other parameter-efficient methods to significantly reduce memory and hardware requirements.

Instructor - Structured Data Extraction

Extracts and validates structured data from LLM responses using Pydantic for reliable, type-safe outputs and automatic retries.

Pinecone Vector Database

Integrates Pinecone's managed vector database to power high-performance RAG, semantic search, and recommendation systems.

Ray Data Scalable Processing

Facilitates high-performance distributed data processing and streaming for large-scale machine learning workloads.

AudioCraft Audio Generation

Generates high-quality music and sound effects from text descriptions using Meta's AudioCraft library.

BigCode Evaluation Harness

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

SimPO LLM Alignment

Implements Simple Preference Optimization to align Large Language Models without requiring a reference model.

Knowledge Distillation for LLMs

Compresses large language models into efficient student models while retaining performance through advanced teacher-student transfer techniques.