Seonglae ChoSupports supervised learning, reinforcement learning (RL), and continuous pre-training through a single YAML configuration file, with immediate deployment via Docker
Axolotl
Axolotl is a tool designed to streamline post-training for various AI models.
Post-training refers to any modifications or additional training performed on
pre-trained models - including full model fine-tuning, parameter-efficient tuning (like
LoRA and QLoRA), supervised fine-tuning (SFT), instruction tuning, and alignment
techniques. With support for multiple model architectures and training configurations,
Axolotl makes it easy to get started with these techniques.
https://docs.axolotl.ai/