AI Engineering

Invoke Skill describes how to call a packaged set of instructions that a user or project has set up for a specific task, including selecting the exact skill name, passing optional arguments, and following the loaded instructions instead of default behavior.

Image to 3D Blueprint analyzes a 2D reference image and outputs a strict 3D production blueprint in JSON, identifying sub-meshes, PBR materials, primitive shapes, boolean operations, and normal-map details.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture for rapid experiment iteration and synthesis. Routes to domain-specific skills, supports continuous operation, and produces research presentations and papers.

AWQ Quantization compresses large language models to 4-bit with activation-aware weight selection. Use it to deploy 7B-70B models on limited GPU memory while keeping accuracy loss low.

Comprehensive guidance for fine-tuning LLMs using Axolotl, including YAML configuration, 100+ model support, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, and multimodal training.

Bitsandbytes Model Quantization loads LLMs in 8-bit or 4-bit to cut GPU memory use and fit larger models. Use it for Hugging Face Transformers inference, QLoRA fine-tuning, or 8-bit optimizers when VRAM is limited.

Constitutional AI trains models with self-critique, revision, and AI feedback to reduce harmful outputs without human labels. Use it when you need safety alignment or a clear set of principles for model behavior.

DeepSpeed provides guidance for distributed training with ZeRO optimization, pipeline parallelism, mixed precision, 1-bit Adam, and sparse attention. Use it when implementing, tuning, or debugging DeepSpeed-based training workflows.

Fine-tune LLMs using reinforcement learning with TRL: SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when you need RLHF, align model with preferences, or train from human feedback.

Flash Attention optimizes transformer attention with Flash Attention for faster inference and lower memory use. Use it for long sequences, GPU memory pressure, or when enabling PyTorch SDPA or flash-attn features.

GGUF Quantization covers GGUF format and llama.cpp quantization for efficient CPU and GPU inference. Use it when converting models for consumer hardware, Apple Silicon, or flexible 2-8 bit local deployment.

GPTQ compresses large language models to 4-bit with minimal accuracy loss. Use it to fit 70B+ models on consumer GPUs or to speed up inference, and with Transformers plus PEFT for QLoRA fine-tuning.