{
  "x402Version": 2,
  "id": 72190,
  "slug": "saylorinnovations-api-ai-hf-datasets",
  "resource": "https://saylorinnovations.com/api/ai/hf-datasets",
  "description": "Search Hugging Face datasets by keyword - downloads, likes, gated flag, last modified, description and tags, sorted by downloads, likes or trending",
  "type": "http",
  "serviceName": "Saylor Innovations Data Desk",
  "mimeType": "application/json",
  "resourceType": "API",
  "accepts": [
    {
      "scheme": "exact",
      "network": "eip155:8453",
      "payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "eip155:137",
      "payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
      "asset": "0x3c499c542cEF5E3811e1192ce70d8cC03d5c3359",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "eip155:42161",
      "payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
      "asset": "0xaf88d065e77c8cC2239327C5EDb3A432268e5831",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7",
      "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7",
      "asset": "Es9vMFrzaCERmJfrF4H2FYD4KCoNkY11McCe8BenwNYB",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7",
      "asset": "So11111111111111111111111111111111111111112",
      "amount": "95877",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    }
  ],
  "outputSchema": {
    "type": "object",
    "properties": {
      "query": {
        "type": "string",
        "description": "The query as the server interpreted it"
      },
      "sort": {
        "type": "string",
        "description": "Sort order applied"
      },
      "count": {
        "type": "number",
        "description": "Number of items returned"
      },
      "datasets": {
        "type": "array"
      },
      "source": {
        "type": "string",
        "description": "Data source the values come from"
      }
    },
    "required": [
      "query",
      "datasets"
    ]
  },
  "extensions": {
    "bazaar": {
      "info": {
        "input": {
          "type": "http",
          "method": "GET",
          "queryParams": {
            "q": "squad",
            "sort": "downloads"
          }
        },
        "output": {
          "type": "json",
          "example": {
            "query": "squad",
            "sort": "downloads",
            "count": 10,
            "datasets": [
              {
                "id": "rajpurkar/squad",
                "author": "rajpurkar",
                "downloads_30d": 208594,
                "likes": 1246,
                "gated": false,
                "last_modified": "2024-03-04T13:54:37.000Z",
                "created": "2022-03-02T23:29:22.000Z",
                "description": "Dataset Card for SQuAD Dataset Summary Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, wh…",
                "tags": [
                  "task_categories:question-answering",
                  "task_ids:extractive-qa",
                  "annotations_creators:crowdsourced"
                ],
                "url": "https://huggingface.co/datasets/rajpurkar/squad"
              },
              {
                "id": "rajpurkar/squad_v2",
                "author": "rajpurkar",
                "downloads_30d": 49512,
                "likes": 268,
                "gated": false,
                "last_modified": "2024-03-04T13:55:27.000Z",
                "created": "2022-03-02T23:29:22.000Z",
                "description": "Dataset Card for SQuAD 2.0 Dataset Summary Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles…",
                "tags": [
                  "task_categories:question-answering",
                  "task_ids:open-domain-qa",
                  "task_ids:extractive-qa"
                ],
                "url": "https://huggingface.co/datasets/rajpurkar/squad_v2"
              },
              {
                "id": "lhoestq/custom_squad",
                "author": "lhoestq",
                "downloads_30d": 16538,
                "likes": 0,
                "gated": false,
                "last_modified": "2022-10-25T09:50:53.000Z",
                "created": "2022-03-02T23:29:22.000Z",
                "description": "Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a s…",
                "tags": [
                  "task_categories:question-answering",
                  "task_ids:extractive-qa",
                  "annotations_creators:crowdsourced"
                ],
                "url": "https://huggingface.co/datasets/lhoestq/custom_squad"
              }
            ],
            "source": "Hugging Face Hub"
          }
        }
      },
      "schema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "input": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "http"
              },
              "method": {
                "type": "string",
                "enum": [
                  "GET"
                ]
              },
              "queryParams": {
                "type": "object",
                "properties": {
                  "q": {
                    "type": "string",
                    "description": "Dataset name or keyword, e.g. squad, code, medical"
                  },
                  "sort": {
                    "type": "string",
                    "description": "optional downloads (default), likes, trendingScore, lastModified, createdAt"
                  }
                },
                "required": [
                  "q"
                ]
              }
            },
            "required": [
              "type",
              "method"
            ],
            "additionalProperties": false
          },
          "output": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "json"
              },
              "example": {
                "type": "object",
                "properties": {
                  "query": {
                    "type": "string",
                    "description": "The query as the server interpreted it"
                  },
                  "sort": {
                    "type": "string",
                    "description": "Sort order applied"
                  },
                  "count": {
                    "type": "number",
                    "description": "Number of items returned"
                  },
                  "datasets": {
                    "type": "array"
                  },
                  "source": {
                    "type": "string",
                    "description": "Data source the values come from"
                  }
                },
                "required": [
                  "query",
                  "datasets"
                ]
              }
            },
            "required": [
              "type"
            ]
          }
        },
        "required": [
          "input"
        ]
      }
    }
  },
  "tags": [
    "hugging face dataset search",
    "find training dataset by topic",
    "most downloaded datasets",
    "huggingface datasets for fine",
    "nlp dataset lookup"
  ],
  "sourceHost": "saylorinnovations.com",
  "lastUpdated": "2026-10-26T22:14:01.862Z",
  "quality": {},
  "metadata": {
    "serviceName": "Saylor Innovations Data Desk",
    "method": "GET",
    "mimeType": "application/json",
    "inputSchema": {
      "type": "object",
      "properties": {
        "q": {
          "type": "string",
          "description": "Dataset name or keyword, e.g. squad, code, medical"
        },
        "sort": {
          "type": "string",
          "description": "optional downloads (default), likes, trendingScore, lastModified, createdAt"
        }
      },
      "required": [
        "q"
      ]
    },
    "exampleResponse": {
      "query": "squad",
      "sort": "downloads",
      "count": 10,
      "datasets": [
        {
          "id": "rajpurkar/squad",
          "author": "rajpurkar",
          "downloads_30d": 208594,
          "likes": 1246,
          "gated": false,
          "last_modified": "2024-03-04T13:54:37.000Z",
          "created": "2022-03-02T23:29:22.000Z",
          "description": "Dataset Card for SQuAD Dataset Summary Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, wh…",
          "tags": [
            "task_categories:question-answering",
            "task_ids:extractive-qa",
            "annotations_creators:crowdsourced"
          ],
          "url": "https://huggingface.co/datasets/rajpurkar/squad"
        },
        {
          "id": "rajpurkar/squad_v2",
          "author": "rajpurkar",
          "downloads_30d": 49512,
          "likes": 268,
          "gated": false,
          "last_modified": "2024-03-04T13:55:27.000Z",
          "created": "2022-03-02T23:29:22.000Z",
          "description": "Dataset Card for SQuAD 2.0 Dataset Summary Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles…",
          "tags": [
            "task_categories:question-answering",
            "task_ids:open-domain-qa",
            "task_ids:extractive-qa"
          ],
          "url": "https://huggingface.co/datasets/rajpurkar/squad_v2"
        },
        {
          "id": "lhoestq/custom_squad",
          "author": "lhoestq",
          "downloads_30d": 16538,
          "likes": 0,
          "gated": false,
          "last_modified": "2022-10-25T09:50:53.000Z",
          "created": "2022-03-02T23:29:22.000Z",
          "description": "Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a s…",
          "tags": [
            "task_categories:question-answering",
            "task_ids:extractive-qa",
            "annotations_creators:crowdsourced"
          ],
          "url": "https://huggingface.co/datasets/lhoestq/custom_squad"
        }
      ],
      "source": "Hugging Face Hub"
    },
    "parameterLocation": "query",
    "extensions": {
      "bazaar": {
        "info": {
          "input": {
            "type": "http",
            "method": "GET",
            "queryParams": {
              "q": "squad",
              "sort": "downloads"
            }
          },
          "output": {
            "type": "json",
            "example": {
              "query": "squad",
              "sort": "downloads",
              "count": 10,
              "datasets": [
                {
                  "id": "rajpurkar/squad",
                  "author": "rajpurkar",
                  "downloads_30d": 208594,
                  "likes": 1246,
                  "gated": false,
                  "last_modified": "2024-03-04T13:54:37.000Z",
                  "created": "2022-03-02T23:29:22.000Z",
                  "description": "Dataset Card for SQuAD Dataset Summary Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, wh…",
                  "tags": [
                    "task_categories:question-answering",
                    "task_ids:extractive-qa",
                    "annotations_creators:crowdsourced"
                  ],
                  "url": "https://huggingface.co/datasets/rajpurkar/squad"
                },
                {
                  "id": "rajpurkar/squad_v2",
                  "author": "rajpurkar",
                  "downloads_30d": 49512,
                  "likes": 268,
                  "gated": false,
                  "last_modified": "2024-03-04T13:55:27.000Z",
                  "created": "2022-03-02T23:29:22.000Z",
                  "description": "Dataset Card for SQuAD 2.0 Dataset Summary Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles…",
                  "tags": [
                    "task_categories:question-answering",
                    "task_ids:open-domain-qa",
                    "task_ids:extractive-qa"
                  ],
                  "url": "https://huggingface.co/datasets/rajpurkar/squad_v2"
                },
                {
                  "id": "lhoestq/custom_squad",
                  "author": "lhoestq",
                  "downloads_30d": 16538,
                  "likes": 0,
                  "gated": false,
                  "last_modified": "2022-10-25T09:50:53.000Z",
                  "created": "2022-03-02T23:29:22.000Z",
                  "description": "Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a s…",
                  "tags": [
                    "task_categories:question-answering",
                    "task_ids:extractive-qa",
                    "annotations_creators:crowdsourced"
                  ],
                  "url": "https://huggingface.co/datasets/lhoestq/custom_squad"
                }
              ],
              "source": "Hugging Face Hub"
            }
          }
        },
        "schema": {
          "$schema": "https://json-schema.org/draft/2020-12/schema",
          "type": "object",
          "properties": {
            "input": {
              "type": "object",
              "properties": {
                "type": {
                  "type": "string",
                  "const": "http"
                },
                "method": {
                  "type": "string",
                  "enum": [
                    "GET"
                  ]
                },
                "queryParams": {
                  "type": "object",
                  "properties": {
                    "q": {
                      "type": "string",
                      "description": "Dataset name or keyword, e.g. squad, code, medical"
                    },
                    "sort": {
                      "type": "string",
                      "description": "optional downloads (default), likes, trendingScore, lastModified, createdAt"
                    }
                  },
                  "required": [
                    "q"
                  ]
                }
              },
              "required": [
                "type",
                "method"
              ],
              "additionalProperties": false
            },
            "output": {
              "type": "object",
              "properties": {
                "type": {
                  "type": "string",
                  "const": "json"
                },
                "example": {
                  "type": "object",
                  "properties": {
                    "query": {
                      "type": "string",
                      "description": "The query as the server interpreted it"
                    },
                    "sort": {
                      "type": "string",
                      "description": "Sort order applied"
                    },
                    "count": {
                      "type": "number",
                      "description": "Number of items returned"
                    },
                    "datasets": {
                      "type": "array"
                    },
                    "source": {
                      "type": "string",
                      "description": "Data source the values come from"
                    }
                  },
                  "required": [
                    "query",
                    "datasets"
                  ]
                }
              },
              "required": [
                "type"
              ]
            }
          },
          "required": [
            "input"
          ]
        }
      }
    },
    "examples": [
      {
        "label": "Unpaid discovery call",
        "method": "GET",
        "url": "https://saylorinnovations.com/api/ai/hf-datasets?q=squad&sort=downloads",
        "expectedStatus": 402
      }
    ],
    "cacheTtlSeconds": 0,
    "capabilities": [],
    "noAccountRequired": true,
    "noApiKeyRequired": true,
    "sideEffects": "Paid calls settle the advertised payment; see the provider contract for execution behavior.",
    "payment": {
      "protocol": "x402",
      "settlement": "direct-to-provider"
    },
    "provider": {
      "name": "Saylor Innovations",
      "host": "saylorinnovations.com",
      "manifestUrl": "https://saylorinnovations.com/.well-known/x402.json"
    }
  },
  "liveness": {
    "reliability": null
  },
  "verified": true,
  "featured": false,
  "provider": {
    "host": "saylorinnovations.com",
    "manifest_name": "Saylor Innovations Knowledge Base",
    "source": "submitted",
    "source_manifest_url": "https://saylorinnovations.com/.well-known/x402.json",
    "submitted_at": "2026-10-26T05:52:02.113Z"
  },
  "exampleResponse": {
    "query": "string",
    "sort": "string",
    "count": 0,
    "datasets": [
      "value"
    ],
    "source": "string"
  }
}