{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2024-0171",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "saiga_llama3_8b: tokenizer change at 91d7b8a (2024-04-25)",
 "details": "saiga_llama3_8b: EOS changed from 128001 to 128009; anything fine-tuned or served against the old value stops at a different token; pad token \"<|reserved_special_token_0|>\" to \"<|im_start|>\"; batched training masks a different id (2024-04-25).\n\nRepository: https://huggingface.co/IlyaGusev/saiga_llama3_8b. Revisions from 91d7b8a51d0dde9658d6f715a01f1ec2cc2a9f50 onward carry this change; a pin at d04705b3c527cc5f5b0ee48c170e4d921cf28d45 or earlier does not.\n\nChanged keys:\n- tokenizer pad_token: <|reserved_special_token_0|> -> <|im_start|> (tokenizer)\n- generation eos_token_id: 128001 -> 128009 (tokenizer)\n- generation pad_token_id: 128002 -> 128000 (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/IlyaGusev/saiga_llama3_8b",
     "events": [
      {
       "introduced": "91d7b8a51d0dde9658d6f715a01f1ec2cc2a9f50"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "IlyaGusev/saiga_llama3_8b",
    "previous_revision": "d04705b3c527cc5f5b0ee48c170e4d921cf28d45"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/IlyaGusev/saiga_llama3_8b/commit/91d7b8a51d0dde9658d6f715a01f1ec2cc2a9f50"
  },
  {
   "type": "PACKAGE",
   "url": "https://huggingface.co/IlyaGusev/saiga_llama3_8b"
  },
  {
   "type": "WEB",
   "url": "https://www.neurarch.com/changes-feeds/models/IlyaGusev/saiga_llama3_8b.html"
  }
 ],
 "database_specific": {
  "source": "neurarch model change tracker",
  "model": "IlyaGusev/saiga_llama3_8b",
  "kind": "tokenizer",
  "classes": [
   "tokenizer"
  ],
  "changed_keys": [
   {
    "file": "tokenizer",
    "key": "pad_token",
    "before": "<|reserved_special_token_0|>",
    "after": "<|im_start|>",
    "class": "tokenizer"
   },
   {
    "file": "generation",
    "key": "eos_token_id",
    "before": 128001,
    "after": 128009,
    "class": "tokenizer"
   },
   {
    "file": "generation",
    "key": "pad_token_id",
    "before": 128002,
    "after": 128000,
    "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": 128001,
    "after": 128009
   },
   "bos": null
  },
  "commit_date": "2024-04-25T18:24:52.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 6,
  "license": "CC-BY-4.0"
 }
}