zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2reward_SFT_reward0
收藏Hugging Face2025-12-05 更新2025-12-20 收录
下载链接:
https://hf-mirror.com/datasets/zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2reward_SFT_reward0
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
features:
- name: prompt_id
dtype: string
- name: prompt
dtype: string
- name: response_0
dtype: string
- name: response_1
dtype: string
- name: response_2
dtype: string
- name: response_3
dtype: string
- name: response_4
dtype: string
- name: response_5
dtype: string
- name: response_6
dtype: string
- name: response_7
dtype: string
- name: response_8
dtype: string
- name: response_9
dtype: string
- name: response_10
dtype: string
- name: response_11
dtype: string
- name: response_12
dtype: string
- name: response_13
dtype: string
- name: response_14
dtype: string
- name: response_15
dtype: string
- name: response_0_reward
list: float64
- name: response_1_reward
list: float64
- name: response_2_reward
list: float64
- name: response_3_reward
list: float64
- name: response_4_reward
list: float64
- name: response_5_reward
list: float64
- name: response_6_reward
list: float64
- name: response_7_reward
list: float64
- name: response_8_reward
list: float64
- name: response_9_reward
list: float64
- name: response_10_reward
list: float64
- name: response_11_reward
list: float64
- name: response_12_reward
list: float64
- name: response_13_reward
list: float64
- name: response_14_reward
list: float64
- name: response_15_reward
list: float64
- name: llama_prompt
dtype: string
- name: llama_prompt_tokens
list: int64
- name: chosen
dtype: string
- name: llama_chosen
dtype: string
- name: llama_chosen_tokens
list: int64
splits:
- name: train
num_bytes: 4124156782
num_examples: 57074
- name: test
num_bytes: 67605496
num_examples: 927
download_size: 1166169507
dataset_size: 4191762278
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---
提供机构:
zjhhhh



