Mitsuki-Sakamoto/alpaca_farm-reward-model-deberta-v3-large-v2-re-preference-64-nsample-2
收藏Hugging Face2024-03-07 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/Mitsuki-Sakamoto/alpaca_farm-reward-model-deberta-v3-large-v2-re-preference-64-nsample-2
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
- config_name: alpaca_instructions-pythia_14m_alpaca_farm_instructions_sft_constant_pa_seed_1
features:
- name: instruction
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: preference
dtype: int64
- name: output_1
dtype: string
- name: output_2
dtype: string
- name: reward_model_prompt_format
dtype: string
- name: gen_prompt_format
dtype: string
- name: gen_kwargs
struct:
- name: do_sample
dtype: bool
- name: max_new_tokens
dtype: int64
- name: pad_token_id
dtype: int64
- name: top_k
dtype: int64
- name: top_p
dtype: float64
- name: reward_1
dtype: float64
- name: reward_2
dtype: float64
- name: n_samples
dtype: int64
splits:
- name: preference
num_bytes: 25315216
num_examples: 20001
download_size: 12112309
dataset_size: 25315216
- config_name: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1
features:
- name: instruction
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: preference
dtype: int64
- name: output_1
dtype: string
- name: output_2
dtype: string
- name: reward_model_prompt_format
dtype: string
- name: gen_prompt_format
dtype: string
- name: gen_kwargs
struct:
- name: do_sample
dtype: bool
- name: max_new_tokens
dtype: int64
- name: pad_token_id
dtype: int64
- name: top_k
dtype: int64
- name: top_p
dtype: float64
- name: reward_1
dtype: float64
- name: reward_2
dtype: float64
- name: n_samples
dtype: int64
splits:
- name: preference
num_bytes: 25451634
num_examples: 20001
download_size: 12144402
dataset_size: 25451634
- config_name: alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1
features:
- name: instruction
dtype: string
- name: input
dtype: string
- name: output
dtype: string
- name: preference
dtype: int64
- name: output_1
dtype: string
- name: output_2
dtype: string
- name: reward_model_prompt_format
dtype: string
- name: gen_prompt_format
dtype: string
- name: gen_kwargs
struct:
- name: do_sample
dtype: bool
- name: max_new_tokens
dtype: int64
- name: pad_token_id
dtype: int64
- name: top_k
dtype: int64
- name: top_p
dtype: float64
- name: reward_1
dtype: float64
- name: reward_2
dtype: float64
- name: n_samples
dtype: int64
splits:
- name: preference
num_bytes: 25276914
num_examples: 20001
download_size: 11799025
dataset_size: 25276914
configs:
- config_name: alpaca_instructions-pythia_14m_alpaca_farm_instructions_sft_constant_pa_seed_1
data_files:
- split: preference
path: alpaca_instructions-pythia_14m_alpaca_farm_instructions_sft_constant_pa_seed_1/preference-*
- config_name: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1
data_files:
- split: preference
path: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/preference-*
- config_name: alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1
data_files:
- split: preference
path: alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1/preference-*
---
提供机构:
Mitsuki-Sakamoto
原始信息汇总
数据集概述
数据集配置
- 配置名称: alpaca_instructions-pythia_14m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 配置名称: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 配置名称: alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1
数据集特征
- 特征名称: instruction
- 数据类型: string
- 特征名称: input
- 数据类型: string
- 特征名称: output
- 数据类型: string
- 特征名称: preference
- 数据类型: int64
- 特征名称: output_1
- 数据类型: string
- 特征名称: output_2
- 数据类型: string
- 特征名称: reward_model_prompt_format
- 数据类型: string
- 特征名称: gen_prompt_format
- 数据类型: string
- 特征名称: gen_kwargs
- 结构:
- 名称: do_sample
- 数据类型: bool
- 名称: max_new_tokens
- 数据类型: int64
- 名称: pad_token_id
- 数据类型: int64
- 名称: top_k
- 数据类型: int64
- 名称: top_p
- 数据类型: float64
- 名称: do_sample
- 结构:
- 特征名称: reward_1
- 数据类型: float64
- 特征名称: reward_2
- 数据类型: float64
- 特征名称: n_samples
- 数据类型: int64
数据集分割
- 分割名称: preference
- 配置: alpaca_instructions-pythia_14m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 字节数: 25315216
- 样本数: 20001
- 配置: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 字节数: 25451634
- 样本数: 20001
- 配置: alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 字节数: 25276914
- 样本数: 20001
- 配置: alpaca_instructions-pythia_14m_alpaca_farm_instructions_sft_constant_pa_seed_1
数据集大小
- 配置: alpaca_instructions-pythia_14m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 下载大小: 12112309
- 数据集大小: 25315216
- 配置: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 下载大小: 12144402
- 数据集大小: 25451634
- 配置: alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 下载大小: 11799025
- 数据集大小: 25276914
数据文件路径
- 配置: alpaca_instructions-pythia_14m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 分割: preference
- 路径: alpaca_instructions-pythia_14m_alpaca_farm_instructions_sft_constant_pa_seed_1/preference-*
- 分割: preference
- 配置: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 分割: preference
- 路径: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/preference-*
- 分割: preference
- 配置: alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 分割: preference
- 路径: alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1/preference-*
- 分割: preference



