{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2020-0025",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "roberta-base-squad2: tokenizer change at deedc3e (2020-11-11)",
 "details": "roberta-base-squad2: tokenizer model_max_length unset to 512; truncation defaults change (2020-11-11).\n\nRepository: https://huggingface.co/deepset/roberta-base-squad2. Revisions from deedc3e42208524e0df3d9149d1f26aa6934f05f onward carry this change; a pin at 596edb02b58a8e188cb86c2f0698e9bf46c83746 or earlier does not.\n\nChanged keys:\n- tokenizer bos_token: <s> -> unset (format-only)\n- tokenizer eos_token: </s> -> unset (format-only)\n- tokenizer model_max_length: unset -> 512 (tokenizer)\n- tokenizer pad_token: <pad> -> unset (format-only)\n- tokenizer unk_token: <unk> -> unset (format-only)\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": "deedc3e42208524e0df3d9149d1f26aa6934f05f"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "deepset/roberta-base-squad2",
    "previous_revision": "596edb02b58a8e188cb86c2f0698e9bf46c83746"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/deepset/roberta-base-squad2/commit/deedc3e42208524e0df3d9149d1f26aa6934f05f"
  },
  {
   "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",
   "format-only"
  ],
  "changed_keys": [
   {
    "file": "tokenizer",
    "key": "bos_token",
    "before": "<s>",
    "after": null,
    "class": "format-only"
   },
   {
    "file": "tokenizer",
    "key": "eos_token",
    "before": "</s>",
    "after": null,
    "class": "format-only"
   },
   {
    "file": "tokenizer",
    "key": "model_max_length",
    "before": null,
    "after": 512,
    "class": "tokenizer"
   },
   {
    "file": "tokenizer",
    "key": "pad_token",
    "before": "<pad>",
    "after": null,
    "class": "format-only"
   },
   {
    "file": "tokenizer",
    "key": "unk_token",
    "before": "<unk>",
    "after": null,
    "class": "format-only"
   }
  ],
  "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": "2020-11-11T13:53:33.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 294,
  "license": "CC-BY-4.0"
 }
}
