{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2020-0039",
 "modified": "2026-11-07T11:55:24.466Z",
 "published": "2026-11-07T11:55:24.466Z",
 "summary": "LaBSE: tokenizer change at 0c5b145 (2020-10-12)",
 "details": "LaBSE: pad token unset to \"[PAD]\"; batched training masks a different id (2020-10-12).\n\nRepository: https://huggingface.co/sentence-transformers/LaBSE. Revisions from 0c5b1457a964062647617135bacba79c0d81fd03 onward carry this change; a pin at f0eff482e167b74a43ed544ceb948aaeaa1c3fa1 or earlier does not.\n\nChanged keys:\n- tokenizer pad_token: unset -> [PAD] (tokenizer)\n- tokenizer unk_token: unset -> [UNK] (tokenizer)\n\nThis record says what the change does mechanically. It is not a report that anything broke for anyone.",
 "affected": [
  {
   "ranges": [
    {
     "type": "GIT",
     "repo": "https://huggingface.co/sentence-transformers/LaBSE",
     "events": [
      {
       "introduced": "0c5b1457a964062647617135bacba79c0d81fd03"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "sentence-transformers/LaBSE",
    "previous_revision": "f0eff482e167b74a43ed544ceb948aaeaa1c3fa1"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/sentence-transformers/LaBSE/commit/0c5b1457a964062647617135bacba79c0d81fd03"
  },
  {
   "type": "PACKAGE",
   "url": "https://huggingface.co/sentence-transformers/LaBSE"
  },
  {
   "type": "WEB",
   "url": "https://www.neurarch.com/changes-feeds/models/sentence-transformers/LaBSE.html"
  }
 ],
 "database_specific": {
  "source": "neurarch model change tracker",
  "model": "sentence-transformers/LaBSE",
  "kind": "tokenizer",
  "classes": [
   "tokenizer"
  ],
  "changed_keys": [
   {
    "file": "tokenizer",
    "key": "pad_token",
    "before": null,
    "after": "[PAD]",
    "class": "tokenizer"
   },
   {
    "file": "tokenizer",
    "key": "unk_token",
    "before": null,
    "after": "[UNK]",
    "class": "tokenizer"
   }
  ],
  "impact": {
   "memory": false,
   "serving": true,
   "tokenizer": true,
   "licence": null
  },
  "breaking": true,
  "breaking_rule": "https://www.neurarch.com/changes-feeds/advisories/index.json#breaking_rule",
  "consequence": {
   "params": null,
   "weightsGbBf16": null,
   "trainPeakGb": null,
   "fingerprint": null,
   "context": null,
   "eos": null,
   "bos": null,
   "derivedSame": true
  },
  "commit_date": "2020-10-12T19:14:44.000Z",
  "detected_at": "2026-11-07T11:55:24.466Z",
  "detected_by": "backfill",
  "days_since_first_commit": 0,
  "license": "CC-BY-4.0"
 }
}
