官方服务:
资源简介:
Different metrics of the sentiment analysis model.
应用场景:
创建时间:
2022-08-24
相关数据集
open-llm-leaderboard-old/details_saberai__Zro1.5_3B
该数据集是在评估模型saberai/Zro1.5_3B时自动创建的,用于Open LLM Leaderboard。数据集包含63个配置,每个配置对应一个评估任务。数据集由一个运行创建,每个运行对应一个特定的分割,分割名称使用运行的时间戳。此外,还有一个名为results的配置,存储所有运行的聚合结果,用于计算和显示Leaderboard上的聚合指标。
Hugging Face2023-12-27 更新320
open-llm-leaderboard-old/details_Gille__StrangeMerges_28-7B-dare_ties
--- pretty_name: Evaluation run of Gille/StrangeMerges_28-7B-dare_ties dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [Gille/StrangeMerges_28-7B-dare_ties](htt
Hugging Face2024-04-02 更新270
katielink/med-gemini-medqa-relabeled
Med-Gemini MedQA Relabelling and Analysis项目对MedQA数据集进行了重新标注和分析,以确保评估结果的可靠性。Med-Gemini模型在医学领域表现出色,但在评估过程中发现MedQA测试集中的一些问题存在标签错误或缺少必要信息。因此,项目团队对MedQA进行了全面重新标注,每个问题至少由三名初级保健医生进行标注,以识别缺失信息和标签错误。重新标注后的数据以C
Hugging Face2024-06-20 更新190
open-llm-leaderboard-old/details_jondurbin__bagel-34b-v0.5
--- pretty_name: Evaluation run of jondurbin/bagel-34b-v0.5 dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [jondurbin/bagel-34b-v0.5](https://huggingface.co/jo
Hugging Face2024-04-17 更新270
open-llm-leaderboard-old/details_louisbrulenaudet__Pearl-7B-0210-ties
--- pretty_name: Evaluation run of louisbrulenaudet/Pearl-7B-0210-ties dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [louisbrulenaudet/Pearl-7B-0210-ties](htt
Hugging Face2024-02-11 更新200



