jbrin/or-bench-balanced
收藏Hugging Face2025-12-05 更新2025-12-20 收录
下载链接：
https://hf-mirror.com/datasets/jbrin/or-bench-balanced
下载链接
链接失效反馈官方服务：
资源简介：
---
dataset_info:
features:
- name: prompt
dtype: string
- name: category
dtype: string
- name: toxicity
dtype: string
splits:
- name: train
num_bytes: 172725
num_examples: 1310
download_size: 76493
dataset_size: 172725
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
license: cc-by-4.0
pretty_name: Balanced OR-Bench
task_categories:
- text-classification
- text-generation
language:
- en
size_categories:
- 1K<n<10K
---
Sourced from: https://huggingface.co/datasets/bench-llm/or-bench
A balanced dataset of toxic and benign prompts from OR-Bench.
提供机构：
jbrin
