Name: haoranli-ml/genvf-multi-policy-train-v1_final_bulle_list
Creator: haoranli-ml
Published: 2026-03-25 03:28:50
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/haoranli-ml/genvf-multi-policy-train-v1_final_bulle_list

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: shard_0_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: dedup_note dtype: string - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 135584353 num_examples: 657 download_size: 53550097 dataset_size: 135584353 - config_name: shard_10_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 138650539 num_examples: 657 download_size: 54353542 dataset_size: 138650539 - config_name: shard_11_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: dedup_note dtype: string - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 140502083 num_examples: 657 download_size: 54287671 dataset_size: 140502083 - config_name: shard_12_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: dedup_note dtype: string - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 132031671 num_examples: 657 download_size: 52283408 dataset_size: 132031671 - config_name: shard_13_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 130740637 num_examples: 657 download_size: 52400678 dataset_size: 130740637 - config_name: shard_14_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: dedup_note dtype: string - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 131708426 num_examples: 657 download_size: 51761117 dataset_size: 131708426 - config_name: shard_15_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 133449730 num_examples: 665 download_size: 52959221 dataset_size: 133449730 - config_name: shard_1_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 131698807 num_examples: 657 download_size: 51879791 dataset_size: 131698807 - config_name: shard_2_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 131136261 num_examples: 657 download_size: 52984214 dataset_size: 131136261 - config_name: shard_3_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 136459851 num_examples: 657 download_size: 54662008 dataset_size: 136459851 - config_name: shard_4_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 135409463 num_examples: 657 download_size: 53252325 dataset_size: 135409463 - config_name: shard_5_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 135273176 num_examples: 657 download_size: 53367371 dataset_size: 135273176 - config_name: shard_6_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 134231671 num_examples: 657 download_size: 52680010 dataset_size: 134231671 - config_name: shard_7_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 133042640 num_examples: 657 download_size: 52864708 dataset_size: 133042640 - config_name: shard_8_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 136169833 num_examples: 657 download_size: 53638533 dataset_size: 136169833 - config_name: shard_9_of_16 features: - name: index dtype: int64 - name: row_id dtype: int64 - name: problem dtype: string - name: answer dtype: string - name: source list: string - name: mean_reward dtype: float64 - name: full_response dtype: string - name: full_reasoning dtype: string - name: model dtype: string - name: prefix dtype: string - name: prefix_end_index dtype: int64 - name: num_thoughts dtype: int64 - name: prefix_type dtype: string - name: prefix_type_description dtype: string - name: suffix_num list: int64 - name: suffix_model list: string - name: pending list: bool - name: pending_model list: 'null' - name: suffix_response list: string - name: suffix_summary list: string - name: self_summary list: string - name: suffix_reasoning list: string - name: finish_reason list: string - name: budget_used list: int64 - name: escalation list: int64 - name: usage list: - name: completion_tokens dtype: int64 - name: prompt_tokens dtype: int64 - name: total_tokens dtype: int64 - name: error list: 'null' - name: error_type list: 'null' - name: prefix_model dtype: string - name: gemini_summary_of_future dtype: string - name: gemini_summary_list list: string - name: prefix_steps list: string - name: suffix_variants list: - name: detailed_steps list: string - name: high_level_steps list: string - name: id dtype: int64 - name: dedup_note dtype: string splits: - name: train num_bytes: 135759438 num_examples: 657 download_size: 53329857 dataset_size: 135759438 configs: - config_name: shard_0_of_16 data_files: - split: train path: shard_0_of_16/train-* - config_name: shard_10_of_16 data_files: - split: train path: shard_10_of_16/train-* - config_name: shard_11_of_16 data_files: - split: train path: shard_11_of_16/train-* - config_name: shard_12_of_16 data_files: - split: train path: shard_12_of_16/train-* - config_name: shard_13_of_16 data_files: - split: train path: shard_13_of_16/train-* - config_name: shard_14_of_16 data_files: - split: train path: shard_14_of_16/train-* - config_name: shard_15_of_16 data_files: - split: train path: shard_15_of_16/train-* - config_name: shard_1_of_16 data_files: - split: train path: shard_1_of_16/train-* - config_name: shard_2_of_16 data_files: - split: train path: shard_2_of_16/train-* - config_name: shard_3_of_16 data_files: - split: train path: shard_3_of_16/train-* - config_name: shard_4_of_16 data_files: - split: train path: shard_4_of_16/train-* - config_name: shard_5_of_16 data_files: - split: train path: shard_5_of_16/train-* - config_name: shard_6_of_16 data_files: - split: train path: shard_6_of_16/train-* - config_name: shard_7_of_16 data_files: - split: train path: shard_7_of_16/train-* - config_name: shard_8_of_16 data_files: - split: train path: shard_8_of_16/train-* - config_name: shard_9_of_16 data_files: - split: train path: shard_9_of_16/train-* ---

应用场景：