相关数据集
open-llm-leaderboard/details_microsoft__DialoGPT-small
--- pretty_name: Evaluation run of microsoft/DialoGPT-small dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [microsoft/DialoGPT-small](https://huggingface.co/mi
Hugging Face2023-12-03 更新410
ostapeno/platy_icl5_maxD50_maxC1000000_prmt20_1
## model_setting_name: platy ## max_context_length: 512 ## icl_examples: 5 ## icl_dataset_name: lukaemon/mmlu ## max_documents_per_subject: 50 ## max_contexts_per_subject: 1000000 ## icl_use_out_optio
Hugging Face2023-10-12 更新160
Automatically Generated Chemical KG
Abstract - In 2020, nearly 3 million scientific and engineering papers were published worldwide (White, K. Publications Output: U.S. Trends And International Comparisons). The vastness of the literatu
DataCite Commons2025-02-11 更新120
open-llm-leaderboard-old/details_ValiantLabs__ShiningValiantXS
该数据集是在Open LLM Leaderboard上对模型ValiantLabs/ShiningValiantXS进行评估时自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。数据集是从3次运行中生成的,每次运行在每个配置中表示为特定的分割,train分割始终指向最新的结果。此外,名为results的配置存储了所有运行的聚合结果,用于计算和显示Open LLM Leaderboard上
Hugging Face2024-01-13 更新190
open-llm-leaderboard-old/details_Josephgflowers__Cinder-Phi-2-Test-1
该数据集是在Open LLM Leaderboard上对模型Josephgflowers/Cinder-Phi-2-Test-1进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。它包含1次运行的结果,每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。此外,还有一个results配置,存储了所有运行的聚合结果,用于计算和显示Open LLM Leaderb
Hugging Face2024-02-19 更新160



