axolotl

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.

BLIP-2 is a vision-language framework that connects a frozen image encoder with a large language model for multimodal tasks. Use it for zero-shot image captioning, visual question answering, or image-text retrieval without task-specific fine-tuning. It's ideal for developers needing to add state-of-the-art visual understanding to LLM-based applications.

This skill integrates Weights & Biases for comprehensive ML experiment tracking and MLOps. It automatically logs metrics, visualizes training in real-time, and manages hyperparameter sweeps and model versions. Use it to compare runs, optimize models, and collaborate within team workspaces directly from your development environment.

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.