{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2023-0021",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "multilingual-e5-small: tokenizer change at 960310a (2023-07-12)",
 "details": "multilingual-e5-small: tokenizer model_max_length 1e+30 to 512; truncation defaults change (2023-07-12).\n\nRepository: https://huggingface.co/intfloat/multilingual-e5-small. Revisions from 960310a7742a4e0a250dd720466bed84fee8caac onward carry this change; a pin at d2648e288f5fe1641aeab663a7fa6d1f0d1daff2 or earlier does not.\n\nChanged keys:\n- tokenizer model_max_length: 1e+30 -> 512 (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/intfloat/multilingual-e5-small",
     "events": [
      {
       "introduced": "960310a7742a4e0a250dd720466bed84fee8caac"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "intfloat/multilingual-e5-small",
    "previous_revision": "d2648e288f5fe1641aeab663a7fa6d1f0d1daff2"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/intfloat/multilingual-e5-small/commit/960310a7742a4e0a250dd720466bed84fee8caac"
  },
  {
   "type": "PACKAGE",
   "url": "https://huggingface.co/intfloat/multilingual-e5-small"
  },
  {
   "type": "WEB",
   "url": "https://www.neurarch.com/changes-feeds/models/intfloat/multilingual-e5-small.html"
  }
 ],
 "database_specific": {
  "source": "neurarch model change tracker",
  "model": "intfloat/multilingual-e5-small",
  "kind": "tokenizer",
  "classes": [
   "tokenizer"
  ],
  "changed_keys": [
   {
    "file": "tokenizer",
    "key": "model_max_length",
    "before": 1e+30,
    "after": 512,
    "class": "tokenizer"
   }
  ],
  "impact": {
   "memory": false,
   "serving": true,
   "tokenizer": true,
   "licence": null
  },
  "breaking": false,
  "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
  },
  "commit_date": "2023-07-12T09:14:02.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 12,
  "license": "CC-BY-4.0"
 }
}