llama-factory

To plan LLaMA-Factory fine-tuning, you can use this Skill to surface official documentation, examples, and configurations for scaffolding end-to-end SFT, RLHF, DPO, and KTO pipelines quickly.

Discovering LLaMA-Factory references for quantization setup involves using this Skill to organize metadata and surface standardized guidance, helping you audit existing pipelines and debug configurations.

Yes, you can use this guidance to onboard new team members to LLaMA-Factory pipelines by surfacing standardized reference structures, official documentation, and best practices for reliable contextual loading.

Yes, this Skill supports DPO and KTO training method discovery by encoding metadata from references and assets to enable reliable navigation across various fine-tuning and inference pipeline topics.

Your LLaMA-Factory SFT setup may lack standardized configuration references because you need consolidated official docs and structured metadata to enable reliable discovery and contextual loading during debugging.

This Skill focuses on organizing and surfacing LLaMA-Factory documentation and references for discovery; it does not execute the training pipelines or generate the model configurations directly.