Name: AISE-TUDelft/StackLessV2_LowLevel
Creator: AISE-TUDelft
Published: 2024-10-09 18:43:38
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/AISE-TUDelft/StackLessV2_LowLevel

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: CommonLispExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exdup_ids_cmlisp_stkv2 sequence: int64 splits: - name: train num_bytes: 296872446 num_examples: 16968 download_size: 110463980 dataset_size: 296872446 - config_name: CommonLispFull features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exdup_ids_cmlisp_stkv2 sequence: int64 - name: near_dups_cmlisp_stkv2 sequence: int64 splits: - name: train num_bytes: 296269615.99363506 num_examples: 16910 download_size: 106452520 dataset_size: 296269615.99363506 - config_name: CommonLispNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exdup_ids_cmlisp_stkv2 sequence: int64 - name: near_dups_cmlisp_stkv2 sequence: int64 splits: - name: train num_bytes: 297285798 num_examples: 16968 download_size: 110586143 dataset_size: 297285798 - config_name: ErlangExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exdup_ids_erlang_stkv2 sequence: int64 splits: - name: train num_bytes: 372615876 num_examples: 32049 download_size: 111106000 dataset_size: 372615876 - config_name: ErlangFull features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exdup_ids_erlang_stkv2 sequence: int64 - name: near_dups_erlang_stkv2 sequence: int64 splits: - name: train num_bytes: 376029971.97241724 num_examples: 31766 download_size: 110236013 dataset_size: 376029971.97241724 - config_name: ErlangNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exdup_ids_erlang_stkv2 sequence: int64 - name: near_dups_erlang_stkv2 sequence: int64 splits: - name: train num_bytes: 379379984 num_examples: 32049 download_size: 113905531 dataset_size: 379379984 - config_name: HaskellExact features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exdup_ids_haskell_stkv2 sequence: int64 splits: - name: train num_bytes: 691141113 num_examples: 111234 download_size: 237138316 dataset_size: 691141113 - config_name: HaskellFull features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exdup_ids_haskell_stkv2 sequence: int64 - name: near_dups_haskell_stkv2 sequence: int64 splits: - name: train num_bytes: 691561422.0806139 num_examples: 110795 download_size: 236560070 dataset_size: 691561422.0806139 - config_name: HaskellNear features: - name: id dtype: int64 - name: file_name dtype: string - name: file_path dtype: string - name: content dtype: string - name: size dtype: int64 - name: language dtype: string - name: extension dtype: string - name: total_lines dtype: int64 - name: avg_line_length dtype: float64 - name: max_line_length dtype: int64 - name: alphanum_fraction dtype: float64 - name: repo_name dtype: string - name: repo_stars dtype: int64 - name: repo_forks dtype: int64 - name: repo_open_issues dtype: int64 - name: repo_license dtype: string - name: repo_extraction_date dtype: string - name: sha dtype: string - name: __index_level_0__ dtype: int64 - name: exdup_ids_haskell_stkv2 sequence: int64 - name: near_dups_haskell_stkv2 sequence: int64 splits: - name: train num_bytes: 694301577 num_examples: 111234 download_size: 238391522 dataset_size: 694301577 configs: - config_name: CommonLispExact data_files: - split: train path: data/CommonLisp_Exact/train-* - config_name: CommonLispFull data_files: - split: train path: data/CommonLisp_Full/train-* - config_name: CommonLispNear data_files: - split: train path: data/CommonLisp_Near/train-* - config_name: ErlangExact data_files: - split: train path: data/Erlang_Exact/train-* - config_name: ErlangFull data_files: - split: train path: data/Erlang_Full/train-* - config_name: ErlangNear data_files: - split: train path: data/Erlang_Near/train-* - config_name: HaskellExact data_files: - split: train path: data/Haskell_Exact/train-* - config_name: HaskellFull data_files: - split: train path: data/Haskell_Full/train-* - config_name: HaskellNear data_files: - split: train path: data/Haskell_Near/train-* ---

应用场景：