{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiefhcb3zzmzsl7icgoec2okni2geqo33fvf4if6pi6rxr6ysdb6n4",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mkn2nfkop332"
  },
  "path": "/t/tiktok-10m-dataset/164640#post_10",
  "publishedAt": "2026-04-29T11:47:24.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "I load it with load_dataset using the raw CSV URL, then switch on streaming so I don’t run out of memory while scanning or sampling videos.",
  "title": "TikTok-10M Dataset"
}