Data Science & ML Claude 技能

OpenAI Whisper Transcription

432

Transcribes audio files into text or JSON format using OpenAI's state-of-the-art Whisper API.

LangChain Framework

384

Builds LLM-powered applications using agents, retrieval-augmented generation (RAG), and modular chains.

LLM Reinforcement Learning & Fine-Tuning

384

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

GPTQ Model Optimization

384

Optimizes Large Language Models using 4-bit post-training quantization to reduce memory usage and accelerate inference on consumer GPUs.

HQQ LLM Quantization

384

Quantizes Large Language Models to 4/3/2-bit precision without calibration data for faster inference and reduced memory footprint.

Axolotl LLM Fine-Tuning

384

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

SimPO LLM Alignment

384

Simplifies large language model alignment using reference-free preference optimization to improve model performance without the overhead of PPO or DPO.

PEFT Fine-Tuning

384

Fine-tunes large language models using LoRA, QLoRA, and other parameter-efficient methods to drastically reduce memory and compute requirements.

Knowledge Distillation for LLMs

384

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

Sentence Transformers

384

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

BigCode Evaluation Harness

384

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

MoE Training (Mixture of Experts)

384

Implements and optimizes Mixture of Experts (MoE) architectures to scale model capacity while reducing training and inference costs.

AWQ LLM Quantization

384

Optimizes Large Language Models using activation-aware 4-bit quantization to achieve 3x inference speedups and significant memory reduction with minimal accuracy loss.

Long Context Transformer Extension

384

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

SGLang Inference Serving

384

Optimizes LLM serving and structured generation using RadixAttention prefix caching for high-performance agentic workflows.

Llama.cpp Inference

384

Deploys and optimizes LLM inference on CPU, Apple Silicon, and consumer hardware using GGUF quantization.

Flash Attention Optimization

384

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

Outlines Structured Generation

384

Guarantees valid, type-safe JSON and structured outputs from Large Language Models using grammar-based constraints.

LLaMA Factory Fine-Tuning

384

Streamlines the fine-tuning process for over 100 large language models using the LLaMA-Factory framework and QLoRA techniques.

AudioCraft AI Generation

384

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

Instructor Structured Outputs

384

Extracts structured, type-safe data from Large Language Models using Pydantic validation and automatic retries.

HuggingFace Accelerate Distributed Training

384

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

OpenRLHF Training Framework

384

Deploys high-performance Reinforcement Learning from Human Feedback (RLHF) workflows using Ray and vLLM acceleration for large-scale model alignment.

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.

Whisper Speech Recognition

384

Transcribes audio, translates speech to English, and automates multilingual audio processing using OpenAI's Whisper models.

Speculative Decoding LLM Accelerator

384

Accelerates LLM inference speeds by up to 3.6x using advanced decoding techniques like Medusa heads and lookahead decoding.

GGUF Quantization & Model Optimization

384

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

LlamaIndex RAG Framework

384

Connects LLMs to private data sources through advanced document ingestion, vector indexing, and retrieval-augmented generation (RAG) pipelines.

PyTorch FSDP Expert

384

Optimizes large-scale AI model training using PyTorch Fully Sharded Data Parallelism for efficient memory management and scaling.