NVIDIA Structured Data Models 实战：零训练完成表格预测
How to Make Zero-Training Tabular Predictions with NVIDIA Structured Data Models
NVIDIA 出了个表格预测库，TabICLv2、KumoRelational 这些预训练模型推理即用，不用自己训练，做表格任务的可以试试。
NVIDIA 发布 Structured Data Models 库，将多个预训练表格基础模型封装在统一 PyTorch 接口下。其中 TabICLv2 和 KumoTabular 处理单张表格，KumoRelational 面向完整关系型数据库。这些模型通过 in-context learning 直接给出预测结果，全程无需训练。本文以教程形式演示如何用该库实现零训练表格预测。
How to Make Zero-Training Tabular Predictions with NVIDIA Structured Data Models
In this tutorial, we implement Structured Data Models, NVIDIA’s new library that puts several pretrained foundation models for tables behind one PyTorch interface, and use it to make predictions without training. The library wraps TabICLv2 and KumoTabular for single tables and KumoRelational for whole relational databases, and each of them answers by in-context learning: we […] The post How to Make Zero-Training Tabular Predictions with NVIDIA Structured Data Models appeared first on MarkTechPost .
- PyTorch10-17 16:00原文
