MWilinski/rlhf-irl
收藏Hugging Face2026-04-15 更新2026-04-26 收录
下载链接：
https://hf-mirror.com/datasets/MWilinski/rlhf-irl
下载链接
链接失效反馈官方服务：
资源简介：
---
dataset_info:
features:
- name: prompt_idx
dtype: int64
- name: system_prompt
dtype: large_string
- name: prompt
list:
- name: content
dtype: string
- name: role
dtype: string
- name: completion
dtype: large_string
- name: system_prompt_type
dtype: large_string
- name: source_dataset
dtype: large_string
- name: helpful_reward
dtype: float64
- name: harmless_reward
dtype: float64
splits:
- name: train
num_bytes: 36810271
num_examples: 10000
- name: test
num_bytes: 15676622
num_examples: 3998
download_size: 24493963
dataset_size: 52486893
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---
提供机构：
MWilinski
