{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2020-0024",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "roberta-base-squad2: tokenizer change at 4aa0450 (2020-04-24)",
 "details": "roberta-base-squad2: EOS declared as 2 (was unset); generation that relied on the library default now stops on this token; pad token unset to 1; batched training masks a different id (2020-04-24).\n\nRepository: https://huggingface.co/deepset/roberta-base-squad2. Revisions from 4aa045039343a5dbb88bab82d8e6a3529ca8a1bc onward carry this change; a pin at 784fa08ee01e943e70962a88f9935514ccf3964e or earlier does not.\n\nChanged keys:\n- eos_token_id: unset -> 2 (tokenizer)\n- pad_token_id: unset -> 1 (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/deepset/roberta-base-squad2",
     "events": [
      {
       "introduced": "4aa045039343a5dbb88bab82d8e6a3529ca8a1bc"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "deepset/roberta-base-squad2",
    "previous_revision": "784fa08ee01e943e70962a88f9935514ccf3964e"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/deepset/roberta-base-squad2/commit/4aa045039343a5dbb88bab82d8e6a3529ca8a1bc"
  },
  {
   "type": "PACKAGE",
   "url": "https://huggingface.co/deepset/roberta-base-squad2"
  },
  {
   "type": "WEB",
   "url": "https://www.neurarch.com/changes-feeds/models/deepset/roberta-base-squad2.html"
  }
 ],
 "database_specific": {
  "source": "neurarch model change tracker",
  "model": "deepset/roberta-base-squad2",
  "kind": "tokenizer",
  "classes": [
   "tokenizer"
  ],
  "changed_keys": [
   {
    "file": "config",
    "key": "eos_token_id",
    "before": null,
    "after": 2,
    "class": "tokenizer"
   },
   {
    "file": "config",
    "key": "pad_token_id",
    "before": null,
    "after": 1,
    "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": {
    "before": null,
    "after": 2
   },
   "bos": null
  },
  "commit_date": "2020-04-24T15:57:45.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 93,
  "license": "CC-BY-4.0"
 }
}
