Data Science & ML Claude 技能

LLaMA Factory Fine-Tuning

384

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

vLLM High-Performance Inference Serving

384

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

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.

LLaVA Multimodal Assistant

384

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

AudioCraft AI Generation

384

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

DSPy Declarative AI Programming

384

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

Whisper Speech Recognition

384

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

Instructor Structured Outputs

384

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

Outlines Structured Generation

384

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

CLIP Vision-Language Model

384

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

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.

BLIP-2 Multimodal Vision

384

Integrates Salesforce's BLIP-2 framework to enable advanced image captioning, visual question answering, and multimodal reasoning within AI workflows.

OpenRLHF Training Framework

384

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

NeMo Curator - GPU Data Curation

384

Curates high-quality datasets for LLM training using GPU-accelerated deduplication, filtering, and PII redaction.

nnsight Model Interpretability

384

Interprets and manipulates neural network internals for any PyTorch model, including massive foundation models via remote execution.

PyTorch FSDP Expert

384

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

pyvene Causal Interventions

384

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

Unsloth Fine-Tuning

384

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

Pinecone Vector Database Integration

384

Manages high-performance vector search and storage for production RAG and AI applications using Pinecone's serverless infrastructure.

LlamaIndex RAG Framework

384

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

Flash Attention Optimization

384

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

Ray Train Distributed Computing

384

Orchestrates distributed machine learning training across clusters to scale PyTorch, TensorFlow, and Hugging Face models.

Model Merging & Fusion

384

Merges multiple fine-tuned AI models using mergekit to combine specialized capabilities like math and coding without expensive retraining.

GRPO RL Fine-Tuning

384

Implements Group Relative Policy Optimization (GRPO) using the TRL library to enhance model reasoning and structured output capabilities.

Llama.cpp Inference

384

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

TensorRT-LLM Optimization

384

Accelerates Large Language Model inference on NVIDIA GPUs using state-of-the-art optimization techniques for maximum throughput and minimal latency.

MLflow Lifecycle Management

384

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

RWKV Model Architecture

384

Implements and optimizes RWKV architectures, a hybrid RNN-Transformer model offering linear-time inference and infinite context windows.