신뢰성있는 모델 파인튜닝 개발 방법

이 글은 신뢰성있는 모델 파인튜닝 개발 방법을 나눔한다.

레퍼런스

• FineTuning PHI-3 for RAG: Why Small Models Are Best for Production | by Nayeem Islam | Medium
• Fine-Tuning Phi-3 with Unsloth: A Beginner-Friendly Guide 🚀🤖 | by Firas Tlili | Medium
• Fine-tuning Small Vision Language Models: Phi-3-vision | by Liana Napalkova, PhD | Medium
• From Scratch: A Deep Dive into Fine-Tuning Phi-3.5 for Clinical Q&A | by Sriman | Medium
• Unsloth Notebooks | Unsloth Documentation
• Unlocking the power of data synthesis for function calling with fine-tuned SLMs | by Kosuke Fujimoto | Data Science + AI at Microsoft | Medium
• PhiCookBook/code/04.Finetuning/Phi-3-finetune-lora-python.ipynb at main · microsoft/PhiCookBook
• Fine-Tuning vs. Function Calling: The New Stack for Customizing Foundation Models | by James Fahey | Medium