JKaiii/assignment4-qwen25-7b-pairrm-lima-dpo
收藏Hugging Face2026-04-28 更新2026-05-03 收录
下载链接：
https://hf-mirror.com/datasets/JKaiii/assignment4-qwen25-7b-pairrm-lima-dpo
下载链接
链接失效反馈官方服务：
资源简介：
---
dataset_info:
features:
- name: instruction
dtype: string
- name: prompt
dtype: string
- name: chosen
dtype: string
- name: rejected
dtype: string
- name: all_responses
sequence: string
- name: pairrm_ranks
sequence: int64
- name: chosen_index
dtype: int64
- name: rejected_index
dtype: int64
splits:
- name: train
num_bytes: 403561
num_examples: 50
download_size: 223865
dataset_size: 403561
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
提供机构：
JKaiii
