探索與導航Hugging Face的模型圖譜

Charting and Navigating Hugging Face's Model Atlas

March 13, 2025

作者: Eliahu Horwitz, Nitzan Kurer, Jonathan Kahana, Liel Amar, Yedid Hoshen

cs.AI

摘要

隨著現今已有數百萬個公開可用的神經網絡，搜尋與分析大型模型庫變得日益重要。在如此眾多的模型中進行導航需要一份地圖集，但由於大多數模型缺乏完善的文檔，繪製這樣的地圖集頗具挑戰性。為了探索模型庫的潛在價值，我們繪製了一份初步的地圖集，代表了Hugging Face平台上已文檔化的部分。這份地圖集提供了模型景觀及其演變的驚人視覺化效果。我們展示了這份地圖集的幾種應用，包括預測模型屬性（例如準確率）以及分析計算機視覺模型的趨勢。然而，由於當前的地圖集仍不完整，我們提出了一種方法來繪製未文檔化的區域。具體而言，我們基於現實世界主流的模型訓練實踐，識別出高置信度的結構先驗。利用這些先驗，我們的方法能夠精確地映射地圖集中先前未文檔化的區域。我們公開釋出了我們的數據集、代碼及互動式地圖集。

English

As there are now millions of publicly available neural networks, searching and analyzing large model repositories becomes increasingly important. Navigating so many models requires an atlas, but as most models are poorly documented charting such an atlas is challenging. To explore the hidden potential of model repositories, we chart a preliminary atlas representing the documented fraction of Hugging Face. It provides stunning visualizations of the model landscape and evolution. We demonstrate several applications of this atlas including predicting model attributes (e.g., accuracy), and analyzing trends in computer vision models. However, as the current atlas remains incomplete, we propose a method for charting undocumented regions. Specifically, we identify high-confidence structural priors based on dominant real-world model training practices. Leveraging these priors, our approach enables accurate mapping of previously undocumented areas of the atlas. We publicly release our datasets, code, and interactive atlas.