LLM-Fine-tuning-QLoRA
PublicIn this repo I have tried to fine-tune a pre-trained LLM (Gemma 3 - 1B) over a "English Quotes" dataset and performed qualitative as well as quantitative evaluation of it. (Part of ES667 Deep Learning Assignment 2)
In this repo I have tried to fine-tune a pre-trained LLM (Gemma 3 - 1B) over a "English Quotes" dataset and performed qualitative as well as quantitative evaluation of it. (Part of ES667 Deep Learning Assignment 2)