Mitsuki-Sakamoto/alpaca_farm-reward-model-deberta-v3-large-v2-re-preference-64-nsample-2-16_mix_random_seed_2
收藏Hugging Face2024-03-25 更新2024-06-11 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-2-16_mix_random_seed_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-1.4b_alpaca_farm_instructions_sft_constant_pa-checkpoint-7500
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
- name: reject_select
dtype: string
- name: index
dtype: int64
splits:
- name: preference
num_bytes: 25889425.028748564
num_examples: 20000
download_size: 12359463
dataset_size: 25889425.028748564
- 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
- name: reject_select
dtype: string
- name: index
dtype: int64
splits:
- name: preference
num_bytes: 25900235.98820059
num_examples: 20000
download_size: 12313149
dataset_size: 25900235.98820059
configs:
- config_name: alpaca_instructions-pythia-1.4b_alpaca_farm_instructions_sft_constant_pa-checkpoint-7500
data_files:
- split: preference
path: alpaca_instructions-pythia-1.4b_alpaca_farm_instructions_sft_constant_pa-checkpoint-7500/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-*
---
提供机构：
Mitsuki-Sakamoto
原始信息汇总
数据集配置信息
配置一
- 配置名称: alpaca_instructions-pythia-1.4b_alpaca_farm_instructions_sft_constant_pa-checkpoint-7500
- 特征:
instruction: 字符串input: 字符串output: 字符串preference: 64位整数output_1: 字符串output_2: 字符串reward_model_prompt_format: 字符串gen_prompt_format: 字符串gen_kwargs: 结构体do_sample: 布尔值max_new_tokens: 64位整数pad_token_id: 64位整数top_k: 64位整数top_p: 64位浮点数
reward_1: 64位浮点数reward_2: 64位浮点数n_samples: 64位整数reject_select: 字符串index: 64位整数
- 分割:
preference:- 字节数: 25889425.028748564
- 样本数: 20000
- 下载大小: 12359463
- 数据集大小: 25889425.028748564
配置二
- 配置名称: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 特征:
instruction: 字符串input: 字符串output: 字符串preference: 64位整数output_1: 字符串output_2: 字符串reward_model_prompt_format: 字符串gen_prompt_format: 字符串gen_kwargs: 结构体do_sample: 布尔值max_new_tokens: 64位整数pad_token_id: 64位整数top_k: 64位整数top_p: 64位浮点数
reward_1: 64位浮点数reward_2: 64位浮点数n_samples: 64位整数reject_select: 字符串index: 64位整数
- 分割:
preference:- 字节数: 25900235.98820059
- 样本数: 20000
- 下载大小: 12313149
- 数据集大小: 25900235.98820059
数据文件信息
配置一
- 配置名称: alpaca_instructions-pythia-1.4b_alpaca_farm_instructions_sft_constant_pa-checkpoint-7500
- 数据文件:
split: preferencepath: alpaca_instructions-pythia-1.4b_alpaca_farm_instructions_sft_constant_pa-checkpoint-7500/preference-*
配置二
- 配置名称: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1
- 数据文件:
split: preferencepath: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/preference-*
