weights-and-biases

This skill quantizes LLMs to 8-bit or 4-bit precision using bitsandbytes, achieving 50-75% memory reduction with minimal accuracy loss. It's ideal for running larger models on limited GPU memory or accelerating inference, supporting formats like INT8, NF4, and FP4. The skill integrates with HuggingFace Transformers and enables QLoRA training and 8-bit optimizers.

This skill provides high-performance tokenization using HuggingFace's Rust-based library, processing 1GB of text in under 20 seconds. It supports BPE, WordPiece, and Unigram algorithms while enabling custom tokenizer training and alignment tracking. Use it when you need production-fast tokenization or to build custom tokenizers integrated with the transformers ecosystem.

This skill enables fine-tuning of LLMs using TRL's reinforcement learning methods including SFT, DPO, and PPO for RLHF and preference alignment. It's designed for aligning models with human feedback and works with HuggingFace Transformers. Use it when you need to implement RLHF, optimize with rewards, or train from human preferences.

CrewAI is a lightweight multi-agent orchestration framework for building teams of specialized AI agents that collaborate autonomously on complex tasks. It enables role-based agent collaboration with memory and supports sequential or hierarchical workflows for production use. The framework is built without LangChain dependencies for lean, fast execution.