Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
5.8
Rating
0
Installs
AI & LLM
Category
This skill provides solid technical guidance for Axolotl LLM fine-tuning with clear YAML configuration patterns, code examples, and organized reference documentation. The description adequately conveys capabilities (FSDP, LoRA/QLoRA, various training methods), and the quick reference section offers practical patterns for common tasks like NCCL testing, FSDP config, and model compression. Structure is good with separation into reference files (api.md, dataset-formats.md, other.md). However, novelty is moderate - while Axolotl is a specialized tool, much of this skill aggregates documentation that could be found through standard searches or the tool's own docs. The skill is most valuable for consolidating scattered information and providing ready-to-use config snippets, but doesn't fundamentally transform how an agent would approach Axolotl tasks compared to browsing documentation directly.
Loading SKILL.md…