Verifying Performance Guidelines for MPI Collectives at Scale - PMBS@SC23 Artifact
收藏NIAID Data Ecosystem2026-05-01 收录
数据链接:
官方服务:
资源简介:
ARTIFACT DESCRIPTION/ARTIFACT EVALUATION
应用场景:
创建时间:
2023-09-28
相关数据集
open-llm-leaderboard/details_CohereForAI__aya-23-8B
该数据集是在评估模型CohereForAI/aya-23-8B时自动创建的,用于Open LLM Leaderboard。数据集由63个配置组成,每个配置对应一个评估任务。数据集由1次运行生成,每次运行可以在每个配置中找到,分割以运行的时间戳命名。train分割始终指向最新结果。results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
Hugging Face2024-05-25 更新200
MBZUAI/cass-bench-v2
--- dataset_info: features: - name: filename dtype: string - name: cuda_source dtype: string - name: cuda_device dtype: string - name: cuda_host dtype: string - name: amd_s
Hugging Face2026-01-04 更新120
Porting DB12 to Python3: Analysis of the scores
DB12 has been originally conceived with Python2 to estimate the power of a given CPU to run HEP applications. However, since January 2020, Python2 is no longer maintained and we decided to port the co
Zenodo2022-08-29 更新40
open-llm-leaderboard/details_raincandy-u__Qwen1.5-1.8B_llamafy
该数据集是在模型raincandy-u/Qwen1.5-1.8B_llamafy在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Ope
Hugging Face2024-04-19 更新160
Additional file 11 of VIBRANT: automated recovery, annotation and curation of microbial viruses, and evaluation of viral community function from genomic sequences
Additional File 11: Table S11. Calculations and results of benchmarking analyses for VIBRANT, VirSorter, VirFinder and MARVEL.
Figshare2020-06-11 更新70



