Data Science & ML Claude 스킬

Ray Data Processing

384

Processes large-scale datasets for machine learning workloads using distributed streaming execution across CPU and GPU clusters.

MLflow Lifecycle Management

384

Manages the machine learning lifecycle by tracking experiments, versioning models, and streamlining production deployments.

FAISS Vector Similarity Search

384

Accelerates large-scale similarity search and clustering for dense vectors using Facebook AI's high-performance library.

PyTorch Lightning Training & Scaling

384

Streamlines deep learning development by decoupling research code from engineering boilerplate for automated distributed training and hardware scaling.

Unsloth Fine-Tuning

384

Accelerates LLM fine-tuning workflows with Unsloth to achieve up to 5x faster training speeds and 80% reduced memory consumption.

CrewAI Multi-Agent Orchestration

384

Orchestrates teams of autonomous AI agents to collaborate on complex tasks through role-based delegation and memory.

Long Context Transformer Extension

384

Extends transformer context windows using RoPE, YaRN, and ALiBi techniques to process documents exceeding 128k tokens.

Segment Anything Model (SAM)

384

Implements Meta AI's foundation model for high-precision zero-shot image segmentation using points, boxes, and masks.

Axolotl LLM Fine-Tuning

384

Streamlines the fine-tuning of large language models using Axolotl through expert YAML configuration guidance and advanced training techniques.

SAELens: Mechanistic Interpretability

384

Decomposes complex neural network activations into sparse, interpretable features to understand and steer model behavior.

Sentence Transformers

384

Generates state-of-the-art text and image embeddings for RAG, semantic search, and clustering tasks.

HuggingFace Tokenizers

384

Provides high-performance, Rust-optimized text tokenization for NLP research and production-grade machine learning pipelines.

LLM Model Pruning

384

Compresses Large Language Models using advanced techniques like Wanda and SparseGPT to reduce memory footprint and accelerate inference speeds.

DeepSpeed Distributed Training

384

Optimizes large-scale AI model training using DeepSpeed's ZeRO, pipeline parallelism, and high-performance DeepNVMe I/O handling.

Stable Diffusion Image Generation

384

Generates high-quality images and performs advanced image transformations using Stable Diffusion models and the HuggingFace Diffusers library.

Weights & Biases MLOps

384

Tracks machine learning experiments and manages model lifecycles with real-time visualization and collaborative tools.

Mamba Architecture & SSM Implementation

384

Implements and optimizes Mamba-based Selective State Space Models for high-efficiency sequence modeling and long-context AI research.

Knowledge Distillation for LLMs

384

Compresses large language models using teacher-student learning techniques to reduce inference costs while maintaining high performance.

LLM Reinforcement Learning & Fine-Tuning

384

Aligns Large Language Models with human preferences using advanced reinforcement learning techniques including SFT, DPO, PPO, and GRPO.

bitsandbytes LLM Quantization

384

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

AudioCraft AI Generation

384

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

Flash Attention Optimization

384

Optimizes Transformer models using Flash Attention to achieve significant speedups and memory reductions during training and inference.

HuggingFace Accelerate Distributed Training

384

Simplifies PyTorch distributed training by providing a unified API for DDP, DeepSpeed, and FSDP with minimal code changes.

LLaVA Multimodal Assistant

384

Enables advanced vision-language capabilities for image understanding, multi-turn visual conversations, and document analysis.

vLLM High-Performance Inference Serving

384

Serves Large Language Models with maximum throughput and efficiency using vLLM's PagedAttention and continuous batching.

DSPy Declarative AI Programming

384

Builds complex AI systems using Stanford's declarative programming framework to optimize prompts and create modular RAG systems automatically.

CLIP Vision-Language Model

384

Enables zero-shot image classification and semantic image search by connecting visual concepts with natural language.

BigCode Evaluation Harness

384

Evaluates AI code generation models across multiple programming languages and benchmarks using standardized pass@k metrics.

GGUF Quantization & Model Optimization

384

Optimizes AI models for efficient local inference using the GGUF format and llama.cpp quantization techniques.

pyvene Causal Interventions

384

Performs declarative causal interventions and mechanistic interpretability experiments on PyTorch models.