Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support. Use when you need flexible fine-tuning with extensive model and method support through simple configuration files.
/plugin marketplace add zechenzhangAGI/AI-research-SKILLs/plugin install axolotl@zechenzhangAGI/AI-research-SKILLs