{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2024-0143",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "gpt-neo-125m: tokenizer change at 21def01 (2024-01-31)",
 "details": "gpt-neo-125m: add_bos_token unset to false; encoding the same text yields different ids; tokenizer_class unset to \"GPT2Tokenizer\" (2024-01-31).\n\nRepository: https://huggingface.co/EleutherAI/gpt-neo-125m. Revisions from 21def0189f5705e2521767faed922f1f15e7d7db onward carry this change; a pin at 0439444c18855fb88213e6e889bf87ffaa96c73e or earlier does not.\n\nChanged keys:\n- tokenizer add_bos_token: unset -> false (tokenizer)\n- tokenizer tokenizer_class: unset -> GPT2Tokenizer (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/EleutherAI/gpt-neo-125m",
     "events": [
      {
       "introduced": "21def0189f5705e2521767faed922f1f15e7d7db"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "EleutherAI/gpt-neo-125m",
    "previous_revision": "0439444c18855fb88213e6e889bf87ffaa96c73e"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/EleutherAI/gpt-neo-125m/commit/21def0189f5705e2521767faed922f1f15e7d7db"
  },
  {
   "type": "PACKAGE",
   "url": "https://huggingface.co/EleutherAI/gpt-neo-125m"
  },
  {
   "type": "WEB",
   "url": "https://www.neurarch.com/changes-feeds/models/EleutherAI/gpt-neo-125m.html"
  }
 ],
 "database_specific": {
  "source": "neurarch model change tracker",
  "model": "EleutherAI/gpt-neo-125m",
  "kind": "tokenizer",
  "classes": [
   "tokenizer"
  ],
  "changed_keys": [
   {
    "file": "tokenizer",
    "key": "add_bos_token",
    "before": null,
    "after": false,
    "class": "tokenizer"
   },
   {
    "file": "tokenizer",
    "key": "tokenizer_class",
    "before": null,
    "after": "GPT2Tokenizer",
    "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
  },
  "commit_date": "2024-01-31T20:29:39.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 1030,
  "license": "CC-BY-4.0"
 }
}