SMASHED is a toolkit designed to apply transformations to samples in datasets, such as fields extraction, tokenization, prompting, batching, and more. Supports datasets from Huggingface, torchdata iterables, or simple lists of dictionaries.

Example code for prefix-tuning GPT/GPT-NeoX models and for inference with trained prefixes

Parameter-efficient automation of data wrangling tasks with prefix-tuning and the T5 language model.

[Paper][Preprint 2024] Multi-domain Knowledge Graph Collaborative Pre-training and Prompt Tuning for Diverse Downstream Tasks

Master Thesis on "Comparing Modular Approaches for Parameter-Efficient Fine-Tuning"

Mitigating bias in pre-trained language models using Prefix-Tuning, focusing on altering word embeddings through contextual orthogonal training, achieving debiasing with minimal parameter training.

Comparison of different adaptation methods on PEFT for fine-tuning downstream tasks or benchmarks.