{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2022-0013",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "bloom-560m: tokenizer change at 8ad61ef (2022-05-28)",
 "details": "bloom-560m: EOS changed from 50256 to 2; anything fine-tuned or served against the old value stops at a different token; BOS changed from 50256 to 1; prompts built by the old tokenizer start with a different token; pad token unset to 3; batched training masks a different id (2022-05-28).\n\nRepository: https://huggingface.co/bigscience/bloom-560m. Revisions from 8ad61ef2f1bf707dcec23c141de73b71e8b04827 onward carry this change; a pin at 5fc13c0bee25a296f39ae3a6d4c8dc8dcb5f4c15 or earlier does not.\n\nChanged keys:\n- bos_token_id: 50256 -> 1 (tokenizer)\n- eos_token_id: 50256 -> 2 (tokenizer)\n- pad_token_id: unset -> 3 (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/bigscience/bloom-560m",
     "events": [
      {
       "introduced": "8ad61ef2f1bf707dcec23c141de73b71e8b04827"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "bigscience/bloom-560m",
    "previous_revision": "5fc13c0bee25a296f39ae3a6d4c8dc8dcb5f4c15"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/bigscience/bloom-560m/commit/8ad61ef2f1bf707dcec23c141de73b71e8b04827"
  },
  {
   "type": "PACKAGE",
   "url": "https://huggingface.co/bigscience/bloom-560m"
  },
  {
   "type": "WEB",
   "url": "https://www.neurarch.com/changes-feeds/models/bigscience/bloom-560m.html"
  }
 ],
 "database_specific": {
  "source": "neurarch model change tracker",
  "model": "bigscience/bloom-560m",
  "kind": "tokenizer",
  "classes": [
   "tokenizer"
  ],
  "changed_keys": [
   {
    "file": "config",
    "key": "bos_token_id",
    "before": 50256,
    "after": 1,
    "class": "tokenizer"
   },
   {
    "file": "config",
    "key": "eos_token_id",
    "before": 50256,
    "after": 2,
    "class": "tokenizer"
   },
   {
    "file": "config",
    "key": "pad_token_id",
    "before": null,
    "after": 3,
    "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": 50256,
    "after": 2
   },
   "bos": {
    "before": 50256,
    "after": 1
   }
  },
  "commit_date": "2022-05-28T18:44:45.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 9,
  "license": "CC-BY-4.0"
 }
}
