context-engineering

Claude skills for LLM engineering tasks including PyTorch, Transformers, LoRA fine-tuning, and MLX on Apple Silicon

Collection of LLM engineering skills for PyTorch, Transformers, LoRA, and MLX

Simplifies machine learning workflows with Apple's MLX framework, enabling efficient tensor operations and neural network development on Apple Silicon.

Implements LoRA fine-tuning techniques for efficient parameter-efficient model adaptation and transfer learning across large language models

Craft precise, effective prompts to maximize AI model performance, optimize response quality, and control output for various use cases

Guides AI model fine-tuning through reinforcement learning with human feedback, improving alignment and performance

Develop, configure, and orchestrate AI agents with advanced prompting, tool integration, and multi-agent collaboration strategies

Efficiently fine-tune large language models using quantized low-rank adaptation for memory-efficient and performant model customization

Streamlines deep learning workflows with PyTorch, enabling efficient model design, training, and deployment across neural network architectures.

Simplifies fine-tuning, inference, and deployment of transformer models like BERT, GPT, and T5 with optimized workflows and best practices