five

Mitsuki-Sakamoto/alpaca_farm-reward-model-deberta-v3-large-v2-re-preference-64-nsample-2_random

收藏
Hugging Face2024-03-10 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_random
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 splits: - name: preference num_bytes: 25669546 num_examples: 20001 download_size: 12196543 dataset_size: 25669546 - 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 splits: - name: preference num_bytes: 25645562 num_examples: 20001 download_size: 12148697 dataset_size: 25645562 - 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 - name: reject_select dtype: string splits: - name: preference num_bytes: 25489159 num_examples: 20001 download_size: 11795765 dataset_size: 25489159 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-* - 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

数据集详情

数据集配置

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
  • 分割
    • preference: 25669546字节,20001个样本
  • 下载大小:12196543字节
  • 数据集大小:25669546字节

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
  • 分割
    • preference: 25645562字节,20001个样本
  • 下载大小:12148697字节
  • 数据集大小:25645562字节

配置名称:alpaca_instructions-pythia_70m_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
  • 分割
    • preference: 25489159字节,20001个样本
  • 下载大小:11795765字节
  • 数据集大小:25489159字节

数据文件

  • 配置名称:alpaca_instructions-pythia-1.4b_alpaca_farm_instructions_sft_constant_pa-checkpoint-7500

    • 分割
      • preference: alpaca_instructions-pythia-1.4b_alpaca_farm_instructions_sft_constant_pa-checkpoint-7500/preference-*
  • 配置名称:alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1

    • 分割
      • preference: alpaca_instructions-pythia_160m_alpaca_farm_instructions_sft_constant_pa_seed_1/preference-*
  • 配置名称:alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1

    • 分割
      • preference: alpaca_instructions-pythia_70m_alpaca_farm_instructions_sft_constant_pa_seed_1/preference-*
二维码
社区交流群
二维码
科研交流群
商业服务