{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2026-0039",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "MoLFormer-XL-both-10pct: tokenizer change at 361063d (2026-07-23)",
 "details": "MoLFormer-XL-both-10pct: EOS declared as \"<eos>\" (was unset); generation that relied on the library default now stops on this token; BOS declared as \"<bos>\" (was unset); tokenizer_class \"MolformerTokenizer\" to \"PreTrainedTokenizerFast\" (2026-07-23).\n\nRepository: https://huggingface.co/ibm-research/MoLFormer-XL-both-10pct. Revisions from 361063d0ad524ef77cf39b08469f6be770dc550f onward carry this change; a pin at abb341ed7cee8c7783088d70bf9f86dff266844e or earlier does not.\n\nChanged keys:\n- tokenizer bos_token: unset -> <bos> (tokenizer)\n- tokenizer eos_token: unset -> <eos> (tokenizer)\n- tokenizer model_max_length: 1e+30 -> unset (format-only)\n- tokenizer tokenizer_class: MolformerTokenizer -> PreTrainedTokenizerFast (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/ibm-research/MoLFormer-XL-both-10pct",
     "events": [
      {
       "introduced": "361063d0ad524ef77cf39b08469f6be770dc550f"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "ibm-research/MoLFormer-XL-both-10pct",
    "previous_revision": "abb341ed7cee8c7783088d70bf9f86dff266844e"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/ibm-research/MoLFormer-XL-both-10pct/commit/361063d0ad524ef77cf39b08469f6be770dc550f"
  },
  {
   "type": "PACKAGE",
   "url": "https://huggingface.co/ibm-research/MoLFormer-XL-both-10pct"
  },
  {
   "type": "WEB",
   "url": "https://www.neurarch.com/changes-feeds/models/ibm-research/MoLFormer-XL-both-10pct.html"
  }
 ],
 "database_specific": {
  "source": "neurarch model change tracker",
  "model": "ibm-research/MoLFormer-XL-both-10pct",
  "kind": "tokenizer",
  "classes": [
   "tokenizer",
   "format-only"
  ],
  "changed_keys": [
   {
    "file": "tokenizer",
    "key": "bos_token",
    "before": null,
    "after": "<bos>",
    "class": "tokenizer"
   },
   {
    "file": "tokenizer",
    "key": "eos_token",
    "before": null,
    "after": "<eos>",
    "class": "tokenizer"
   },
   {
    "file": "tokenizer",
    "key": "model_max_length",
    "before": 1e+30,
    "after": null,
    "class": "format-only"
   },
   {
    "file": "tokenizer",
    "key": "tokenizer_class",
    "before": "MolformerTokenizer",
    "after": "PreTrainedTokenizerFast",
    "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": "<eos>"
   },
   "bos": {
    "before": null,
    "after": "<bos>"
   }
  },
  "commit_date": "2026-07-23T14:28:52.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 1006,
  "license": "CC-BY-4.0"
 }
}
