Large Language Model Fine-Tuning with PEFT and LoRA (Practical Implementation)

This video explains how to fine-tune large language model (e.g, Flan-t5-base) efficiently using PEFT (Parameter-Efficient Fine-Tuning) and LoRA (Low-Rank Adaptation). This approach reduces computational costs while maintaining high performance. [code]: https://github.com/manishasirsat/peft_llm_tuning [dataset]: https://huggingface.co/datasets/knkarthick/dialogsum [paper]: 1) Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., ... & Chen, W. (2021). Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685; 2) Xu, L., Xie, H., Qin, S. Z. J., Tao, X., & Wang, F. L. (2023). Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assessment. arXiv preprint arXiv:2312.12148. -------------------------------------------------------------------------------------------------------------------------------------------------------------- 1. Generative AI Playlist: https://www.youtube.com/watch?v=ID04YmgzM38&list=PLzkBTicHqQFmdF62zHHramnBRZl6zUvmR 2. Deep Learning Playlist: https://www.youtube.com/playlist?list=PLzkBTicHqQFmY89SS1Xkfe-gpGCr-XGJo&jct=a2fQJbo-0p7KqCRdDNC9lSdLYCPcag -------------------------------------------------------------------------------------------------------------------------------------------------------------- Connect with me on social media platforms: Website: https://ai-researchstudies.com/ Google scholar: https://scholar.google.com/citations?user=kM4QN-8AAAAJ&hl=en LinkedIn: https://www.linkedin.com/in/manishasirsat GitHub:https://github.com/manishasirsat Quora: https://machinelearningresearch.quora.com/ Blogger: https://manisha-sirsat.blogspot.com/ Twitter: https://twitter.com/ManishaSirsat ⏱️ Timestamps 0:00 Intro 0:46 why LoRA PEFT is needed? 5:53 LLM fine-tuning: a practical demo