zjhhhh/7b_iter1_rlcf_rlcf_expand_tokenized
收藏Hugging Face2025-11-21 更新2025-12-20 收录
下载链接：
https://hf-mirror.com/datasets/zjhhhh/7b_iter1_rlcf_rlcf_expand_tokenized
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: requirements
dtype: string
- name: selection_response_1
dtype: string
- name: selection_response_2
dtype: string
- name: selection_response_3
dtype: string
- name: selection_response_4
dtype: string
- name: base_response_1
dtype: string
- name: base_response_2
dtype: string
- name: current_response_1
dtype: string
- name: current_response_2
dtype: string
- name: selection_1_mean
list: float64
- name: selection_1_majority
list: float64
- name: selection_1_reward
dtype: float64
- name: selection_2_mean
list: float64
- name: selection_2_majority
list: float64
- name: selection_2_reward
dtype: float64
- name: selection_3_mean
list: float64
- name: selection_3_majority
list: float64
- name: selection_3_reward
dtype: float64
- name: selection_4_mean
list: float64
- name: selection_4_majority
list: float64
- name: selection_4_reward
dtype: float64
- name: base_1_mean
list: float64
- name: base_1_majority
list: float64
- name: base_1_reward
dtype: float64
- name: base_2_mean
list: float64
- name: base_2_majority
list: float64
- name: base_2_reward
dtype: float64
- name: current_1_mean
list: float64
- name: current_1_majority
list: float64
- name: current_1_reward
dtype: float64
- name: current_2_mean
list: float64
- name: current_2_majority
list: float64
- name: current_2_reward
dtype: float64
- name: qwen_prompt
dtype: string
- name: qwen_prompt_tokens
list: int64
- name: chosen
dtype: string
- name: reject
dtype: string
- name: qwen_chosen
dtype: string
- name: qwen_reject
dtype: string
- name: qwen_chosen_tokens
list: int64
- name: qwen_reject_tokens
list: int64
- name: chosen_reward
dtype: float64
- name: reject_reward
dtype: float64
- name: g_chosen
dtype: float64
- name: g_reject
dtype: float64
splits:
- name: train
num_bytes: 24380581123
num_examples: 255277
- name: test
num_bytes: 69317388
num_examples: 737
download_size: 2125096570
dataset_size: 24449898511
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---
提供机构：
zjhhhh
