TransformerRanker: A Tool for Efficiently Finding the Best-Suited Language Models for Downstream Classification Tasks
This addresses a practical problem for NLP practitioners by providing an efficient tool to reduce computational costs in model selection, though it is incremental as it builds on existing transferability estimation methods.
The paper tackles the challenge of selecting the best pre-trained language model for downstream classification tasks by introducing TransformerRanker, a lightweight library that efficiently ranks models without fine-tuning, achieving state-of-the-art rankings as shown in empirical results.
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.