A from-scratch PyTorch implementation of Low-Rank Adaptation (LoRA) to efficiently fine-tune BERT models for text classification. This project compares the performance and parameter efficiency of LoRA, full fine-tuning, and from-scratch training.
python nlp machine-learning text-classification university-project pytorch transformer course-project lora knowledge-distillation comparative-analysis fine-tuning peft tiny-bert low-rank-adaptation parameter-efficient-fine-tuning
-
Updated
Oct 29, 2025 - Python