====== LLM Fine-Tuning ======

  * [[https://huggingface.co/blog/trl-peft|Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU]]
  * [[https://towardsdatascience.com/fine-tuning-llms-on-a-single-consumer-graphic-card-6de1587daddb|Fine Tuning LLMs on a Single Consumer Graphic Card]]
  * [[https://medium.com/@geronimo7/phinetuning-2-0-28a2be6de110|Phinetuning 2.0]]
  * [[https://lightning.ai/lightning-ai/studios/code-lora-from-scratch?view=public&section=all|Code LoRA from Scratch]]
  * [[https://huggingface.co/blog/peft|PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware]]


==== PEFT ====

{{topic>LLM튜닝 PEFT LoRA &rsort&simplelist}}

==== RLHF ====

{{topic>RLHF 선호학습 &rsort&simplelist}}