在模型hosted_vllm//fsx/anton/deepseek-r1-checkpoint的评估运行过程中自动创建的数据集。包含13个配置，每个配置对应一个评估任务。数据集由7次运行生成，每次运行在各个配置中都有对应的分割，使用运行时戳命名。"train"分割始终指向最新结果。另外，还有一个名为"results"的配置，用于存储所有运行的聚合结果。

Hugging Face2025-01-31 更新110

Dataset of attitude towards statistics

心理测量

学科评估

Data is collected postgraduate students. Attitudes Toward Statistics (ATS) tool has been used to collect the data. There are two dimensions measuring the attitude of students towards the field of sta

NIAID Data Ecosystem80

SuperGPQA

语言模型评估

学科评估

This repository contains the data presented in [SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines](https://huggingface.co/papers/2502.14739). ## Tutorials for submitting to the offi

魔搭社区2026-06-24 更新450

Programas académicos en el Ranking de Shanghai 2019 de Universidades Colombianas

高等教育排名

学科评估

Ranking de Shanghai 2019 Programas académicos en el Ranking de Shanghai 2019 de Universidades Colombianas Fuente: http://www.shanghairanking.com/es/

NIAID Data Ecosystem80