Generate Axolotl YAML configurations for LoRA/QLoRA and preference-based training.
npx skills add https://github.com/cabezno/bmb-encover-agent --skill axolotl-cabezno
Please help me install this Agent Skill. Skill: axolotl Source: https://github.com/cabezno/bmb-encover-agent/tree/main/skills/mlops/training/axolotl Command: npx skills add https://github.com/cabezno/bmb-encover-agent --skill axolotl-cabezno
Axolotl-fine-tuning YAML configs can be complex and easy to misconfigure, causing slow training, incorrect masking, or inefficient multi-GPU behavior; this Skill streamlines building and troubleshooting Axolotl training setups.
Use the axolotl skill to generate an Axolotl YAML configuration for LoRA fine-tuning with DPO for your chosen dataset format and then validate critical performance settings like FSDP or context parallelism.
High-intent search queries and answers about installing and using this skill.
To configure LoRA fine-tuning in an Axolotl YAML file, you define specific dataset mappings and LoRA parameters. This skill generates correct YAML configurations to prevent incorrect masking and ensure efficient training runs.
Setting up multi-GPU training with FSDP in Axolotl requires adjusting specific performance knobs in your YAML config. This skill provides guidance on FSDP settings, context parallelism, and distributed batching to prevent inefficient scaling.
Yes, you can use Axolotl for DPO and other preference-based LLM training workflows. This skill supports building YAML recipes for SFT as well as DPO, KTO, ORPO, and GRPO preference training methods.
LLM fine-tuning runs fail due to incorrect dataset masking from misconfigured Axolotl YAML settings. This skill applies documentation-derived guidance to correctly reference dataset and API specifics, preventing masking errors.
To debug slow LLM training performance in Axolotl, you adjust FSDP settings, context parallelism, and compressed checkpoint saving. This skill provides quick-reference patterns for common configuration mistakes and optimization steps.
aayushsoamFine-tune Large Language Models with Axolotl using YAML configurations.
BagelHoleSet up QLoRA, LoRA, and full fine-tuning infrastructure with Hugging Face TRL and Axolotl.
Supporter09Convert PyTorch models into LightningModule and Trainer workflows.
twjarviszyra-webConfigure Axolotl YAML for LLM fine-tuning and evaluation workflows.
