public/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: 670c6014808ab5626f024866
      id: mrs83/kurtis_mental_health_initial
      author: mrs83
      cardData: {"language": ["en"], "dataset_info": {"features": [{"name": "question", "dtype": "string"}, {"name": "answer", "dtype": "string"}, {"name": "dataset_name", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 11631854, "num_examples": 11491}], "download_size": 5523582, "dataset_size": 11631854}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]}
      disabled: False
      gated: False
      lastModified: 2024-10-17T22:35:25.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: df642e83a81f878f20698e8f1d4d5a72bd246a1b
      description: None
      downloads: 0
      tags: ['language:en', 'size_categories:10K<n<100K', 'format:parquet', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2024-10-14T00:04:36.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 6705aa23fc0a446f3828b487
      id: PhdDz/BioASQBlurb_5_WITH_RELATION_vqc_hetionet
      author: PhdDz
      cardData: None
      disabled: False
      gated: False
      lastModified: 2024-10-08T21:54:45.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: dad09e125f900058d19d61bd271ae31da51a3a13
      description: None
      downloads: 0
      tags: ['size_categories:n<1K', 'format:json', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2024-10-08T21:54:43.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 66224e1f57abf1be69a75bf8
      id: baraah/test3
      author: baraah
      cardData: {"license": "unknown"}
      disabled: False
      gated: False
      lastModified: 2024-04-19T10:58:14.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: 6b8100193e14e05868357832fedb1ee13370afb0
      description: None
      downloads: 0
      tags: ['license:unknown', 'size_categories:n<1K', 'format:arrow', 'modality:text', 'library:datasets', 'library:mlcroissant', 'region:us']
      createdAt: 2024-04-19T10:57:35.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 66f2d5543c2fc5c666fbd345
      id: yifangong/split_candidate_dataset_part_3
      author: yifangong
      cardData: None
      disabled: False
      gated: False
      lastModified: 2024-09-24T15:17:47.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: 929634d2c425a1f3f4f73e958fa4d80ca075030f
      description: None
      downloads: 0
      tags: ['size_categories:1K<n<10K', 'format:json', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2024-09-24T15:05:56.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 6503a1fcd25ce81dfcd3bf3d
      id: UniverseTBD/arxiv-bit-flip-cs.LG
      author: UniverseTBD
      cardData: {"dataset_info": {"features": [{"name": "bit", "dtype": "string"}, {"name": "flip", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "categories", "dtype": "string"}, {"name": "abstract", "dtype": "string"}, {"name": "authors", "dtype": "string"}, {"name": "doi", "dtype": "string"}, {"name": "id", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 229044314, "num_examples": 100039}], "download_size": 127335112, "dataset_size": 229044314}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]}
      disabled: False
      gated: False
      lastModified: 2023-09-24T00:11:18.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: 27e335094496235ca60ce4699913cddb0f151956
      description: 
	
		
	
	
		Dataset Card for "arxiv-bit-flip-cs.LG"
	

This dataset contains "Bit-Flips," structured representations extracted from the abstracts of ArXiv papers, specifically in the category of cs.LG (Machine Learning). These Bit-Flips aim to encapsulate the essence of the research by identifying the conventional belief or 'status quo' the abstract challenges (Bit) and the counterargument or innovative approach that flips the Bit (Flip).

	
		
	
	
		Bit-Flip Concept
	

A Bit-Flip serves as a… See the full description on the dataset page: https://huggingface.co/datasets/UniverseTBD/arxiv-bit-flip-cs.LG.
      downloads: 0
      tags: ['size_categories:100K<n<1M', 'format:parquet', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2023-09-15T00:14:52.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 6634b75562f76fd1804e4368
      id: open-llm-leaderboard-old/details_Cesco2004__TW3CESCO.V2
      author: open-llm-leaderboard-old
      cardData: None
      disabled: False
      gated: False
      lastModified: 2024-05-03T10:07:34.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: 8bb697ed40be7783a62296ab4ed9ec0855afd8ca
      description: None
      downloads: 0
      tags: ['region:us']
      createdAt: 2024-05-03T10:07:17.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 63b64340c5a5432fd86317b4
      id: irds/mmarco_v2_fr_dev
      author: irds
      cardData: {"pretty_name": "`mmarco/v2/fr/dev`", "viewer": false, "source_datasets": ["irds/mmarco_v2_fr"], "task_categories": ["text-retrieval"], "language": ["fr"]}
      disabled: False
      gated: False
      lastModified: 2024-10-04T14:31:33.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: d8bce2de2fe67c7edfbfe4944fc9517ec7c6fec2
      description: 
	
		
	
	
		Dataset Card for mmarco/v2/fr/dev
	

The mmarco/v2/fr/dev dataset, provided by the ir-datasets package.
For more information about the dataset, see the documentation.

	
		
	
	
		Data
	

This dataset provides:

queries (i.e., topics); count=101,093

qrels: (relevance assessments); count=59,273

For docs, use irds/mmarco_v2_fr



	
		
	
	
		Usage
	

from datasets import load_dataset

queries = load_dataset('irds/mmarco_v2_fr_dev', 'queries')
for record in queries:
    record #… See the full description on the dataset page: https://huggingface.co/datasets/irds/mmarco_v2_fr_dev.
      downloads: 0
      tags: ['task_categories:text-retrieval', 'source_datasets:irds/mmarco_v2_fr', 'language:fr', 'arxiv:2108.13897', 'region:us']
      createdAt: 2023-01-05T03:25:52.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 651d7fe027f248c7abadc0ca
      id: autoevaluate/autoeval-eval-imdb-plain_text-e61a98-47317145210
      author: autoevaluate
      cardData: None
      disabled: False
      gated: False
      lastModified: 2023-10-04T15:08:20.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: c6247ff8381adbb8b5ac19441aa2781a9628a4ec
      description: None
      downloads: 0
      tags: ['region:us']
      createdAt: 2023-10-04T15:08:16.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 6577f1600e0d4703ffa89c1f
      id: debadas/diamonds
      author: debadas
      cardData: {"license": "mit", "dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "stock_number", "dtype": "string"}, {"name": "shape", "dtype": "string"}, {"name": "carat", "dtype": "float64"}, {"name": "clarity", "dtype": "string"}, {"name": "colour", "dtype": "string"}, {"name": "cut", "dtype": "string"}, {"name": "polish", "dtype": "string"}, {"name": "symmetry", "dtype": "string"}, {"name": "fluorescence", "dtype": "string"}, {"name": "lab", "dtype": "string"}, {"name": "length", "dtype": "float64"}, {"name": "width", "dtype": "float64"}, {"name": "depth", "dtype": "float64"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 4796614925.89, "num_examples": 48765}], "download_size": 3319091745, "dataset_size": 4796614925.89}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]}
      disabled: False
      gated: False
      lastModified: 2023-12-12T06:33:23.000Z
      likes: 0
      trendingScore: 0.0
      private: False
      sha: ef6f3d675fce2fc89e9b90009d4f9a760d54497a
      description: None
      downloads: 2
      tags: ['license:mit', 'size_categories:10K<n<100K', 'format:parquet', 'modality:image', 'modality:text', 'library:datasets', 'library:dask', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2023-12-12T05:36:32.000Z
      key: 
      paperswithcode_id: None
      citation: None
    - _id: 65a9cbb30150f64adf7977c7
      id: MetalZuna/System_Prompts
      author: MetalZuna
      cardData: {"license": "mit"}
      disabled: False
      gated: False
      lastModified: 2024-01-19T01:14:37.000Z
      likes: 3
      trendingScore: 0.0
      private: False
      sha: 3728325044250993ea7403f7a5833ee8514f5c38
      description: None
      downloads: 1
      tags: ['license:mit', 'size_categories:n<1K', 'format:csv', 'modality:text', 'library:datasets', 'library:pandas', 'library:mlcroissant', 'library:polars', 'region:us']
      createdAt: 2024-01-19T01:09:07.000Z
      key: 
      paperswithcode_id: None
      citation: None