TransformerRanker: A Tool for Efficiently Finding the Best-Suited Language Models for Downstream Classification Tasks

TL;DR

TransformerRanker is an open-source library that efficiently ranks pre-trained language models for NLP classification tasks without extensive fine-tuning, using transferability estimation methods to identify the most suitable models.

Contribution

It introduces a lightweight, easy-to-use ranking tool that combines transferability estimation techniques with layer aggregation for selecting optimal PLMs for downstream tasks.

Findings

State-of-the-art ranking accuracy demonstrated

Efficient ranking without costly fine-tuning

Easy integration with HuggingFace ecosystem

Abstract

Classification tasks in NLP are typically addressed by selecting a pre-trained language model (PLM) from a model hub, and fine-tuning it for the task at hand. However, given the very large number of PLMs that are currently available, a practical challenge is to determine which of them will perform best for a specific downstream task. With this paper, we introduce TransformerRanker, a lightweight library that efficiently ranks PLMs for classification tasks without the need for computationally costly fine-tuning. Our library implements current approaches for transferability estimation (LogME, H-Score, kNN), in combination with layer aggregation options, which we empirically showed to yield state-of-the-art rankings of PLMs (Garbas et al., 2024). We designed the interface to be lightweight and easy to use, allowing users to directly connect to the HuggingFace Transformers and Dataset libraries. Users need only select a downstream classification task and a list of PLMs to create a ranking of likely best-suited PLMs for their task. We make TransformerRanker available as a pip-installable open-source library https://github.com/flairNLP/transformer-ranker.