at://samuel.bsky.team/app.bsky.feed.post/3ktwmoplyzt2h

Back to Collection

Record JSON

{
  "$type": "app.bsky.feed.post",
  "createdAt": "2024-06-02T09:15:44.481Z",
  "embed": {
    "$type": "app.bsky.embed.external",
    "external": {
      "description": "\u003cp\u003eWe present a dataset of 5,85 billion CLIP-filtered image-text pairs, 14x bigger than LAION-400M, previously the biggest openly accessible image-text datas...",
      "thumb": {
        "$type": "blob",
        "ref": {
          "$link": "bafkreidtofx5i5zlkhvz6nclyks4d67bwrnsxzmt3xzwdgi6wj523r24my"
        },
        "mimeType": "image/jpeg",
        "size": 418590
      },
      "title": "LAION-5B: A NEW ERA OF OPEN LARGE-SCALE MULTI-MODAL DATASETS | LAION",
      "uri": "https://laion.ai/blog/laion-5b/"
    }
  },
  "facets": [
    {
      "features": [
        {
          "$type": "app.bsky.richtext.facet#link",
          "uri": "https://laion.ai/blog/laion-5b/"
        }
      ],
      "index": {
        "byteEnd": 156,
        "byteStart": 133
      }
    }
  ],
  "langs": [
    "en"
  ],
  "reply": {
    "parent": {
      "cid": "bafyreicqxxd2zfg3uttwkzihyyzg6vvhzfeegf3ifnwuzukcqh2jteoa3e",
      "uri": "at://did:plc:jiqeoqryjeg76qf4b3jl6xb2/app.bsky.feed.post/3ktwmjjcgyk2h"
    },
    "root": {
      "cid": "bafyreieydhqrgycerevhjw2ammdzq5dhxdemavzdqaygqplbscndlzfim4",
      "uri": "at://did:plc:p2cp5gopk7mgjegy6wadk3ep/app.bsky.feed.post/3ktwlwdsbit2h"
    }
  },
  "text": "we don’t know because it hasn’t been released yet, but most are based on the Laion-5b dataset, which is taken from Common Crawl\n\nlaion.ai/blog/laion-5b/"
}