five

distilabel-internal-testing/reward-bench-critique-alpacaeval-easy

收藏
Hugging Face2024-04-04 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/distilabel-internal-testing/reward-bench-critique-alpacaeval-easy
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: response dtype: string - name: model dtype: string - name: subset dtype: string - name: id dtype: int64 - name: is_chosen dtype: bool splits: - name: train num_bytes: 302896 num_examples: 200 download_size: 168802 dataset_size: 302896 configs: - config_name: default data_files: - split: train path: data/train-* --- ## Description This dataset is a small subset of [`allenai/reward-bench`](https://huggingface.co/datasets/allenai/reward-bench) to test with our critique models. It was generated in the following way: ```python from datasets import Dataset import pandas as pd from datasets import load_dataset ds = load_dataset("allenai/reward-bench", split="filtered") data = [] for row in ds.filter(lambda x: x["subset"] == "alpacaeval-easy"): for response in ["chosen", "rejected"]: model, is_chosen = (row["chosen_model"], True) if response == "chosen" else (row["rejected_model"], False) data.append( { "prompt": row["prompt"], "response": row[response], "model": model, "subset": row["subset"], "id": row["id"], "is_chosen": is_chosen } ) subset = Dataset.from_pandas(pd.DataFrame(data)) subset.push_to_hub("distilabel-internal-testing/reward-bench-critique-alpacaeval-easy", private=True, split="train") ``` ### Example row ```json { "prompt": "How do I detail a car?", "response": "Detailing a car involves a thorough cleaning inside and out, as well as polishing and waxing to protect the vehicle's surfaces. Here's a step-by-step guide to detailing a car:\n\n**Exterior Detailing:**\n\n1. **Wash the Car:**\n - Rinse the car with water to remove loose dirt.\n - Use a car wash soap and microfiber wash mitt to clean the car from top to bottom.\n - Clean the wheels and tires with a brush and a wheel cleaner.\n - Rinse the car thoroughly to remove all soap.\n\n2. **Dry the Car:**\n - Use a microfiber towel or a chamois to dry the car to prevent water spots.\n\n3. **Clay Bar Treatment:**\n - Use a clay bar with a lubricant to remove embedded surface contaminants from the paint.\n\n4. **Polishing:**\n - Apply car polish with a dual-action polisher or by hand to correct paint imperfections and create a smooth surface.\n\n5. **Waxing:**\n - Apply a coat of wax or paint sealant to protect the paint and give it a glossy finish.\n\n6. **Windows and Mirrors:**\n - Clean the windows and mirrors with a glass cleaner and a microfiber towel.\n\n7. **Tire and Trim Dressing:**\n - Apply a tire dressing to the tires for a shiny finish.\n - Use a trim restorer or protectant on plastic and rubber parts to prevent fading.\n\n**Interior Detailing:**\n\n1. **Remove Trash:**\n - Clear out any trash and remove personal items from the car.\n\n2. **Vacuum:**\n - Vacuum the seats, carpets, floor mats, and trunk.\n - Use a brush attachment for the dashboard and door panels.\n\n3. **Shampoo Carpets and Upholstery:**\n - Use a carpet cleaner and a brush to clean the carpets and upholstery.\n - For leather interiors, use a leather cleaner and conditioner.\n\n4. **Clean Hard Surfaces:**\n - Wipe down all hard surfaces (dashboard, center console, door panels, etc.) with a mild all-purpose cleaner and a microfiber cloth.\n\n5. **Windows and Mirrors:**\n - Clean the interior side of windows and mirrors.\n\n6. **Air Vents and Crevices:**\n - Use a detailing brush or compressed air to clean out air vents and hard-to-reach crevices.\n\n7. **Final Touches:**\n - Apply a protectant to the dashboard and other plastic components.\n - Replace air fresheners if needed.\n\n**Additional Tips:**\n\n- Work in the shade or a cool, well-ventilated garage to prevent products from drying too quickly and leaving residue.\n- Use separate buckets for washing and rinsing to avoid contaminating the clean water with dirt.\n- Always use gentle, non-abrasive materials and cleaners specifically designed for automotive use to avoid damaging surfaces.\n- Move in a systematic way to ensure you don't miss any spots.\n\nBy following these steps, you'll give your car a thorough clean that not only makes it look great but also helps in maintaining its value. Remember, regular detailing can prevent wear and tear and keep your car looking new for years to come.", "model": "GPT4-Turbo", "subset": "alpacaeval-easy", "id": 30, "is_chosen": true } ```

数据集信息: 特征: - 字段名:prompt(提示词),数据类型:字符串 - 字段名:response(回复),数据类型:字符串 - 字段名:model(模型),数据类型:字符串 - 字段名:subset(子集),数据类型:字符串 - 字段名:id(编号),数据类型:64位整数 - 字段名:is_chosen(是否为优选回复),数据类型:布尔值 数据拆分: - 名称:训练集(train),字节大小:302896,样本数量:200 下载体积:168802 数据集总字节大小:302896 配置: - 配置名称:默认配置(default),数据文件: - 数据拆分:训练集,路径:data/train-* ## 数据集说明 本数据集为 [`allenai/reward-bench`](https://huggingface.co/datasets/allenai/reward-bench) 的小型子集,用于配合我们的评判模型开展测试。 其生成代码如下: python from datasets import Dataset import pandas as pd from datasets import load_dataset ds = load_dataset("allenai/reward-bench", split="filtered") data = [] for row in ds.filter(lambda x: x["subset"] == "alpacaeval-easy"): for response in ["chosen", "rejected"]: model, is_chosen = (row["chosen_model"], True) if response == "chosen" else (row["rejected_model"], False) data.append( { "prompt": row["prompt"], "response": row[response], "model": model, "subset": row["subset"], "id": row["id"], "is_chosen": is_chosen } ) subset = Dataset.from_pandas(pd.DataFrame(data)) subset.push_to_hub("distilabel-internal-testing/reward-bench-critique-alpacaeval-easy", private=True, split="train") ### 示例数据行 json { "prompt": "如何给汽车做美容养护?", "response": "汽车美容养护包含对车身内外的深度清洁,以及抛光、打蜡以保护车辆表面。以下为汽车美容养护的分步指南: **外部美容养护:** 1. **清洗车辆:** - 先用清水冲洗车身,去除松散污垢。 - 使用洗车液与超细纤维洗车手套,从车顶至车身底部依次清洁车辆。 - 使用刷子与轮毂清洁剂清洁车轮与轮胎。 - 彻底冲洗车身,去除所有残留皂液。 2. **擦干车辆:** - 使用超细纤维毛巾或麂皮擦干车身,避免产生水渍。 3. **黏土抛光处理:** - 使用黏土配合润滑剂,去除车漆表面嵌入的污染物。 4. **抛光处理:** - 使用双向抛光机或手工方式涂抹汽车抛光剂,修正漆面瑕疵,打造光滑表面。 5. **打蜡养护:** - 涂抹一层蜡或漆面密封剂,保护漆面并赋予光泽质感。 6. **车窗与后视镜清洁:** - 使用玻璃清洁剂与超细纤维毛巾清洁车窗与后视镜。 7. **轮胎与饰件护理:** - 涂抹轮胎光亮剂,赋予轮胎光泽质感。 - 使用塑料与橡胶件还原剂或保护剂,防止部件褪色老化。 **内部美容养护:** 1. **清理杂物:** - 清除车内所有垃圾与个人物品。 2. **吸尘清洁:** - 对座椅、地毯、脚垫与后备箱进行吸尘处理。 - 使用毛刷配件清洁仪表盘与车门饰板。 3. **地毯与内饰清洁:** - 使用地毯清洁剂与毛刷清洁地毯与内饰织物。 - 对于皮革内饰,使用皮革清洁剂与护理剂进行养护。 4. **硬质表面清洁:** - 使用温和的全能清洁剂与超细纤维布,擦拭所有硬质表面(仪表盘、中控台、车门饰板等)。 5. **车窗与后视镜内部清洁:** - 清洁车窗与后视镜的内侧表面。 6. **出风口与缝隙清洁:** - 使用细节刷或压缩空气,清洁空调出风口与难以触及的缝隙。 7. **最终收尾:** - 为仪表盘与其他塑料部件涂抹保护剂。 - 按需更换车载香薰。 **额外小贴士:** - 在阴凉处或通风良好的车库内作业,避免产品过快干燥留下残留痕迹。 - 使用分开的水桶分别盛装清洗液与冲洗水,避免污垢污染清洁用水。 - 始终使用温和、无研磨性的专用汽车清洁产品与材料,避免损伤车辆表面。 - 按系统流程作业,确保无遗漏区域。 按照上述步骤操作,您可让爱车获得深度清洁,不仅外观焕然一新,更有助于维持车辆保值率。请记住,定期美容养护可预防磨损老化,让爱车常年如新。", "model": "GPT4-Turbo", "subset": "alpacaeval-easy", "id": 30, "is_chosen": true }
提供机构:
distilabel-internal-testing
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作