Guide YAML-config driven LLM fine-tuning with Axolotl.
npx skills add https://github.com/ever-oli/io --skill axolotl-ever-oli
Please help me install this Agent Skill. Skill: axolotl Source: https://github.com/ever-oli/io/tree/main/skills/mlops/training/axolotl Command: npx skills add https://github.com/ever-oli/io --skill axolotl-ever-oli
Axolotl provides expert guidance for fine-tuning large language models with YAML-driven workflows, enabling efficient experimentation.
Run an Axolotl fine-tuning workflow using a YAML config to start a new LLM experiment.
High-intent search queries and answers about installing and using this skill.
LoRA and QLoRA are supported parameter-efficient fine-tuning methods for LLMs in Axolotl. They allow you to adapt large models by training a small number of parameters, reducing memory requirements during the fine-tuning workflow.
DPO, ORPO, and GRPO are supported alignment methods for language model training in Axolotl. These approaches allow you to refine model behavior based on human preferences without needing complex reinforcement learning loops.
Multimodal training is supported for large language models in Axolotl. You can configure experiments using YAML to train models on datasets that combine text with other data types across research and production pipelines.
Integrate reference docs into LLM fine-tuning by using the CLI and reference documentation integration provided by Axolotl. This supports scalable ML engineering workflows and helps apply prompt strategies during training.
fikriafFine-tune Large Language Models using YAML configurations and Axolotl.
Supporter09Configure and troubleshoot LLaMA-Factory LLM fine-tuning workflows end to end.
zerwizConfigure and troubleshoot Axolotl YAML training workflows for LLM fine-tuning.
huggingfaceTrain and fine-tune language models on Hugging Face Jobs using TRL methods.
