skills.rest
HugoAlmeidaMoreira
HugoAlmeidaMoreiraCOMMUNITY
Explore all skills by this author →
GitHub

axolotl

Fine-tune large language models with YAML configs and LoRA adapters.

Updated Aug 27, 2026
Search Tags:#llm#fine-tuning#yaml#lora#dpo#rlhf#grpo
One-click install
npx skills add https://github.com/HugoAlmeidaMoreira/zeus-agent --skill axolotl-hugoalmeidamoreira
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: axolotl
Source: https://github.com/HugoAlmeidaMoreira/zeus-agent/tree/main/skills/mlops/training/axolotl
Command: npx skills add https://github.com/HugoAlmeidaMoreira/zeus-agent --skill axolotl-hugoalmeidamoreira

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Axolotl simplifies configuring and executing YAML-driven fine-tuning of LLMs with adapters like LoRA, DPO, and GRPO, reducing setup time and error-prone scripting.

Core Features & Use Cases

  • YAML-based fine-tuning of LLMs with LoRA and post-training methods (DPO, GRPO, ORPO, KTO).
  • Supports supervised fine-tuning, RLHF workflows, and multi-architecture adaptation across common model families.
  • Real-world scenario: a team wants to adapt a base model to a domain using a YAML config and a small set of adapters.

Quick Start

Run a YAML-based training config to fine-tune an LLM with LoRA, DPO, or GRPO using Axolotl.

Frequently Asked Questions about axolotl

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fine-tune an LLM using YAML configurations?▼

You can fine-tune an LLM using YAML configurations by defining training specs for LoRA-based adapters and supervised fine-tuning. This approach orchestrates the training workflow without error-prone scripting, reducing setup time.

Can I use YAML configs to run RLHF workflows with DPO and GRPO?▼

Yes, YAML configs can run RLHF workflows using DPO, GRPO, ORPO, and KTO methods. These post-training methods are orchestrated through YAML-based training specs to execute adapter-based training workflows.

What is the best way to adapt a base model to a specific domain with LoRA?▼

The best way to adapt a base model to a domain with LoRA is using YAML-driven training specs and a small set of adapters. This simplifies multi-architecture adaptation across common model families for your specific domain.

Does YAML-driven fine-tuning support supervised fine-tuning across diverse architectures?▼

Yes, YAML-driven fine-tuning supports supervised fine-tuning across diverse architectures. It uses YAML-based training specs to orchestrate LoRA adapters and related training workflows across common model families.

Why use YAML-based training specs instead of manual scripting for LLM fine-tuning?▼

You use YAML-based training specs for LLM fine-tuning to reduce setup time and eliminate error-prone scripting. YAML configurations simplify the orchestration of LoRA, DPO, and GRPO training methods across common model families.

Related Skills

Explore More Software Engineering Skills→
CUexterCUexter
2

simpo-training

Automate reference-free preference optimization for LLM alignment with PyTorch.

Community
Advanced
nahisahonahisaho
3

scientific-transfer-learning

Fine-tune pre-trained models on domain-specific scientific datasets with transfer learning workflows.

Community
Advanced
automatedigitalautomatedigital
1

axolotl

Configure and execute LLM fine-tuning workflows with the Axolotl framework.

Official
Advanced
niznik-devniznik-dev
16

Design Experiment

Plan LLM fine-tuning and evaluation experiments with YAML summaries and JSONL audit logs.

Community
Advanced