andrewsiah/Personalization_Bench_w_dpa

---
dataset_info:
features:
- name: prompt
dtype: string
- name: subset
dtype: string
- name: prompt_id
dtype: int64
- name: response_1
dtype: string
- name: response_1_model
dtype: string
- name: response_2
dtype: string
- name: response_2_model
dtype: string
- name: response_3
dtype: string
- name: response_3_model
dtype: string
- name: response_4
dtype: string
- name: response_4_model
dtype: string
- name: response_5
dtype: string
- name: response_5_model
dtype: string
- name: response_6
dtype: string
- name: response_6_model
dtype: string
- name: response_7
dtype: string
- name: response_7_model
dtype: string
- name: response_8
dtype: string
- name: response_8_model
dtype: string
- name: response_1_gemma_2b
dtype: float64
- name: response_2_gemma_2b
dtype: float64
- name: response_3_gemma_2b
dtype: float64
- name: response_4_gemma_2b
dtype: float64
- name: response_5_gemma_2b
dtype: float64
- name: response_6_gemma_2b
dtype: float64
- name: response_7_gemma_2b
dtype: float64
- name: response_8_gemma_2b
dtype: float64
- name: response_1_mistral_dpa
dtype: float64
- name: response_2_mistral_dpa
dtype: float64
- name: response_3_mistral_dpa
dtype: float64
- name: response_4_mistral_dpa
dtype: float64
- name: response_5_mistral_dpa
dtype: float64
- name: response_6_mistral_dpa
dtype: float64
- name: response_7_mistral_dpa
dtype: float64
- name: response_8_mistral_dpa
dtype: float64
- name: response_1_oasst_deberta_v3
dtype: float64
- name: response_2_oasst_deberta_v3
dtype: float64
- name: response_3_oasst_deberta_v3
dtype: float64
- name: response_4_oasst_deberta_v3
dtype: float64
- name: response_5_oasst_deberta_v3
dtype: float64
- name: response_6_oasst_deberta_v3
dtype: float64
- name: response_7_oasst_deberta_v3
dtype: float64
- name: response_8_oasst_deberta_v3
dtype: float64
- name: response_1_gemma_7b
dtype: float64
- name: response_2_gemma_7b
dtype: float64
- name: response_3_gemma_7b
dtype: float64
- name: response_4_gemma_7b
dtype: float64
- name: response_5_gemma_7b
dtype: float64
- name: response_6_gemma_7b
dtype: float64
- name: response_7_gemma_7b
dtype: float64
- name: response_8_gemma_7b
dtype: float64
- name: response_1_mistral_raft
dtype: float64
- name: response_2_mistral_raft
dtype: float64
- name: response_3_mistral_raft
dtype: float64
- name: response_4_mistral_raft
dtype: float64
- name: response_5_mistral_raft
dtype: float64
- name: response_6_mistral_raft
dtype: float64
- name: response_7_mistral_raft
dtype: float64
- name: response_8_mistral_raft
dtype: float64
- name: response_1_mistral_ray
dtype: float64
- name: response_2_mistral_ray
dtype: float64
- name: response_3_mistral_ray
dtype: float64
- name: response_4_mistral_ray
dtype: float64
- name: response_5_mistral_ray
dtype: float64
- name: response_6_mistral_ray
dtype: float64
- name: response_7_mistral_ray
dtype: float64
- name: response_8_mistral_ray
dtype: float64
- name: response_1_mistral_weqweasdas
dtype: float64
- name: response_2_mistral_weqweasdas
dtype: float64
- name: response_3_mistral_weqweasdas
dtype: float64
- name: response_4_mistral_weqweasdas
dtype: float64
- name: response_5_mistral_weqweasdas
dtype: float64
- name: response_6_mistral_weqweasdas
dtype: float64
- name: response_7_mistral_weqweasdas
dtype: float64
- name: response_8_mistral_weqweasdas
dtype: float64
- name: response_1_llama3_sfairx
dtype: float64
- name: response_2_llama3_sfairx
dtype: float64
- name: response_3_llama3_sfairx
dtype: float64
- name: response_4_llama3_sfairx
dtype: float64
- name: response_5_llama3_sfairx
dtype: float64
- name: response_6_llama3_sfairx
dtype: float64
- name: response_7_llama3_sfairx
dtype: float64
- name: response_8_llama3_sfairx
dtype: float64
- name: id
dtype: int64
splits:
- name: train
num_bytes: 140282405
num_examples: 9431
- name: test
num_bytes: 15319270
num_examples: 1000
download_size: 91389476
dataset_size: 155601675
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---

This dataset is primarily used for evaluating and comparing the generation capabilities of different natural language processing models. It includes multiple prompts and their corresponding responses generated by various models, along with scores for these responses. The dataset is divided into training and test sets, suitable for model training and performance evaluation.

原始信息汇总

数据集概述

数据集特征

• prompt: 数据类型为字符串（string）。
• subset: 数据类型为字符串（string）。
• prompt_id: 数据类型为整数（int64）。
• response_1 至 response_8: 数据类型为字符串（string）。
• response_1_model 至 response_8_model: 数据类型为字符串（string）。
• response_1_gemma_2b 至 response_8_gemma_2b: 数据类型为浮点数（float64）。
• response_1_mistral_dpa 至 response_8_mistral_dpa: 数据类型为浮点数（float64）。
• response_1_oasst_deberta_v3 至 response_8_oasst_deberta_v3: 数据类型为浮点数（float64）。
• response_1_gemma_7b 至 response_8_gemma_7b: 数据类型为浮点数（float64）。
• response_1_mistral_raft 至 response_8_mistral_raft: 数据类型为浮点数（float64）。
• response_1_mistral_ray 至 response_8_mistral_ray: 数据类型为浮点数（float64）。
• response_1_mistral_weqweasdas 至 response_8_mistral_weqweasdas: 数据类型为浮点数（float64）。
• response_1_llama3_sfairx 至 response_8_llama3_sfairx: 数据类型为浮点数（float64）。
• id: 数据类型为整数（int64）。

数据集划分

• train: 包含9431个样本，总大小为140282405字节。
• test: 包含1000个样本，总大小为15319270字节。

数据集大小

• 下载大小: 91389476字节。
• 数据集总大小: 155601675字节。

配置

• config_name: default
• data_files:
  • train: 路径为data/train-*。
  • test: 路径为data/test-*。