tables/datasets.example.yaml

datasets:
  table_structure:
    - column: _id
      type: VARCHAR
    - column: id
      type: VARCHAR
    - column: author
      type: VARCHAR
    - column: cardData
      type: VARCHAR
    - column: disabled
      type: BOOLEAN
    - column: gated
      type: VARCHAR
    - column: lastModified
      type: VARCHAR
    - column: likes
      type: BIGINT
    - column: trendingScore
      type: DOUBLE
    - column: private
      type: BOOLEAN
    - column: sha
      type: VARCHAR
    - column: description
      type: VARCHAR
    - column: downloads
      type: BIGINT
    - column: tags
      type: VARCHAR[]
    - column: createdAt
      type: VARCHAR
    - column: key
      type: VARCHAR
    - column: paperswithcode_id
      type: VARCHAR
    - column: citation
      type: VARCHAR
  random_items:
    - _id: 64c38c73a8de22f7a1a6c7e1
      id: C-MTEB/EcomRetrieval-qrels
      author: C-MTEB
      cardData: {"configs": [{"config_name": "default", "data_files": [{"split": "dev", "path": "data/dev-*"}]}], "dataset_info": {"features": [{"name": "qid", "dtype": "string"}, {"name": "pid", "dtype": "string"}, {"name": "score", "dtype": "int64"}], "splits": [{"name": "dev", "num_bytes": 27890, "num_examples": 1000}], "download_size": 14540, "dataset_size": 27890}}
      disabled: False
      gated: False
      lastModified: 2023-07-28T09:37:58.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: 39c90699b034ec22ac45b3abf5b0bbb5ffd421f9
      description: 
	
		
	
	
		Dataset Card for "EcomRetrieval-qrels"
	

More Information needed

      downloads: 2893
      tags: ['size_categories:1K<n<10K', 'format:parquet', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2023-07-28T09:37:55.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 6571a64493ea01156d9c5f2b
      id: topeomole/fin
      author: topeomole
      cardData: None
      disabled: False
      gated: False
      lastModified: 2023-12-29T08:49:31.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: 6e68c3a7cce23e0e650997d672fbef009b14af32
      description: None
      downloads: 0
      tags: ['size_categories:10K<n<100K', 'format:csv', 'modality:text', 'library:datasets', 'library:dask', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2023-12-07T11:02:28.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 659193db35c41262d6a53f71
      id: greathero/evenmorex11-newthreeclass-newercontrailsvalidationdataset
      author: greathero
      cardData: {"dataset_info": {"features": [{"name": "pixel_values", "dtype": "image"}, {"name": "label", "dtype": "image"}], "splits": [{"name": "train", "num_bytes": 162552, "num_examples": 9}], "download_size": 38146, "dataset_size": 162552}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]}
      disabled: False
      gated: False
      lastModified: 2023-12-31T19:12:42.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: b7b5c1282518329689aba655335e218e79831e97
      description: None
      downloads: 0
      tags: ['size_categories:n<1K', 'format:parquet', 'modality:image', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2023-12-31T16:16:27.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 62d3dd1ac85b0fcf7fd98c9d
      id: Maxmioti/GDRP-fines
      author: Maxmioti
      cardData: {"license": "other"}
      disabled: False
      gated: False
      lastModified: 2022-07-17T10:03:34.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: 85b9612b440ac0158d5722d0d45b849a012468ec
      description: Opensource DataSet form a Kaggle competition https://www.kaggle.com/datasets/andreibuliga1/gdpr-fines-20182020-updated-23012021
GDPR-fines is a dataset with summary of GDPR cases from companies that were find between 2018 and 2021. You will find the summary plus the Articles violated in the cases (3 most importants + "Others" regrouping the rest of articles).
Raw text and lemmatized text available plus multi-labels.

      downloads: 0
      tags: ['license:other', 'size_categories:n<1K', 'format:csv', 'modality:tabular', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2022-07-17T09:57:46.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 65f4980b0a4480a3d52dbbf3
      id: reach-vb/mls-eng-10k-repunct-test-v4
      author: reach-vb
      cardData: {"dataset_info": {"features": [{"name": "original_path", "dtype": "string"}, {"name": "begin_time", "dtype": "float64"}, {"name": "end_time", "dtype": "float64"}, {"name": "transcript", "dtype": "string"}, {"name": "audio_duration", "dtype": "float64"}, {"name": "speaker_id", "dtype": "string"}, {"name": "book_id", "dtype": "string"}, {"name": "repunct_text", "dtype": "string"}], "splits": [{"name": "dev", "num_bytes": 2182587, "num_examples": 3807}], "download_size": 1221776, "dataset_size": 2182587}, "configs": [{"config_name": "default", "data_files": [{"split": "dev", "path": "data/dev-*"}]}]}
      disabled: False
      gated: False
      lastModified: 2024-03-15T18:48:45.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: 0f7c184d7e9f0f69babcca664bac0fcda107ef17
      description: None
      downloads: 0
      tags: ['size_categories:1K<n<10K', 'format:parquet', 'modality:tabular', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2024-03-15T18:48:43.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 661fa0bcb0e9b7e049a9202b
      id: atluzz/train_doc_en_jsonl
      author: atluzz
      cardData: {"license": "apache-2.0"}
      disabled: False
      gated: False
      lastModified: 2024-04-24T10:38:19.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: 5aba071b4fb548841207b134d5f22f981a3ba89b
      description: None
      downloads: 0
      tags: ['license:apache-2.0', 'size_categories:n<1K', 'format:json', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2024-04-17T10:13:16.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 662ed2502e1ed663bc3570c9
      id: leharris3/airline_reviews_servq
      author: leharris3
      cardData: {"license": "mit"}
      disabled: False
      gated: False
      lastModified: 2024-04-30T00:16:58.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: cf7deac5762779e544ed94d8445d074725d42cd3
      description: None
      downloads: 0
      tags: ['license:mit', 'size_categories:10K<n<100K', 'format:csv', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2024-04-28T22:48:48.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 6670d2f2b0cc541843371fb4
      id: rahulsikder223/SentEval-CR
      author: rahulsikder223
      cardData: {"dataset_info": {"features": [{"name": "sentence", "dtype": "string"}, {"name": "label", "dtype": "int64"}], "splits": [{"name": "train", "num_bytes": 288477.7054304636, "num_examples": 2642}, {"name": "test", "num_bytes": 123711.29456953642, "num_examples": 1133}], "download_size": 246421, "dataset_size": 412189}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "test", "path": "data/test-*"}]}]}
      disabled: False
      gated: False
      lastModified: 2024-06-18T00:40:19.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: b092bc7763a0514f2c454d001abdfbf138a6be74
      description: This is the SentEval Customer Reviews dataset which has been divided into train and test splits. Here, the labels are binary where 1 corresponds to 'Positive Reviews' and 0 corresponds to 'Negative Reviews'.

      downloads: 18
      tags: ['size_categories:1K<n<10K', 'format:parquet', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2024-06-18T00:21:06.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 6412397cbf081e031e9391a7
      id: fathyshalab/reklamation24_wasser-strom-gas-intent
      author: fathyshalab
      cardData: {"dataset_info": {"features": [{"name": "text", "dtype": "string"}, {"name": "label", "dtype": "int64"}, {"name": "__index_level_0__", "dtype": "int64"}], "splits": [{"name": "train", "num_bytes": 203230, "num_examples": 383}, {"name": "test", "num_bytes": 52516, "num_examples": 96}], "download_size": 142247, "dataset_size": 255746}}
      disabled: False
      gated: False
      lastModified: 2023-03-15T22:09:40.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: c8d8322e9e75b8c81eb9b31eb4f4ad9a420f6dbb
      description: 
	
		
	
	
		Dataset Card for "reklamation24_wasser-strom-gas-intent"
	

More Information needed

      downloads: 0
      tags: ['size_categories:n<1K', 'format:parquet', 'modality:tabular', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2023-03-15T21:32:44.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 66071d3e8ea886bc670da278
      id: BangumiBase/saijakutamerwagomihiroinotabiwohajimemashita
      author: BangumiBase
      cardData: {"license": "mit", "tags": ["art"], "size_categories": ["1K<n<10K"]}
      disabled: False
      gated: False
      lastModified: 2024-03-30T01:28:15.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: ecf08621c8d5dc8d1051abdad6568f99e20b9bd0
      description: 
	
		
	
	
		Bangumi Image Base of Saijaku Tamer Wa Gomi Hiroi No Tabi Wo Hajimemashita
	

This is the image base of bangumi Saijaku Tamer wa Gomi Hiroi no Tabi wo Hajimemashita, we detected 81 characters, 6058 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate… See the full description on the dataset page: https://huggingface.co/datasets/BangumiBase/saijakutamerwagomihiroinotabiwohajimemashita.
      downloads: 0
      tags: ['license:mit', 'size_categories:1K<n<10K', 'modality:image', 'region:us', 'art']
      createdAt: 2024-03-29T19:57:50.000Z
      key: 
      paperswithcode_id: None
      citation: None