training-llms-megatron

OpenRLHF is a high-performance RLHF training framework for fine-tuning large language models (7B-70B+ parameters) using methods like PPO, DPO, and GRPO. It leverages Ray for distributed architecture and vLLM for accelerated inference, achieving speeds 2x faster than alternatives like DeepSpeedChat. Use this skill when you need efficient, distributed RLHF training with optimized GPU resource sharing and ZeRO-3 support.

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.

The qdrant-vector-search skill provides a high-performance vector similarity search engine for building production RAG systems. It enables fast nearest neighbor search, hybrid search with filtering, and scalable vector storage powered by Rust. Use it when you need low-latency semantic search with horizontal scaling capabilities and full data control.

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.