{
 "schema_version": "1.7.0",
 "id": "x_NXMC-2025-0105",
 "modified": "2026-10-19T02:33:38.839Z",
 "published": "2026-10-18T09:00:52.565Z",
 "summary": "Llama-3.2-1B-Instruct: tokenizer change at 0430e71 (2025-01-22)",
 "details": "Llama-3.2-1B-Instruct: pad token unset to 128004; batched training masks a different id; the chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering; add_bos_token unset to true; encoding the same text yields different ids (2025-01-22).\n\nRepository: https://huggingface.co/unsloth/Llama-3.2-1B-Instruct. Revisions from 0430e7102ae7f4fad2b056a4d5064abd985588fc onward carry this change; a pin at bd6d97814a86488154b2032080b776ca831e5547 or earlier does not.\n\nChanged keys:\n- pad_token_id: unset -> 128004 (tokenizer)\n- tokenizer add_bos_token: unset -> true (tokenizer)\n- tokenizer chat_template_sha256: 5816fce10444e03c -> 053402b579e589c0 (template)\n- generation max_length: unset -> 131072 (generation-defaults)\n- generation pad_token_id: unset -> 128004 (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/unsloth/Llama-3.2-1B-Instruct",
     "events": [
      {
       "introduced": "0430e7102ae7f4fad2b056a4d5064abd985588fc"
      }
     ]
    }
   ],
   "database_specific": {
    "model": "unsloth/Llama-3.2-1B-Instruct",
    "previous_revision": "bd6d97814a86488154b2032080b776ca831e5547"
   }
  }
 ],
 "references": [
  {
   "type": "INTRODUCED",
   "url": "https://huggingface.co/unsloth/Llama-3.2-1B-Instruct/commit/0430e7102ae7f4fad2b056a4d5064abd985588fc"
  },
  {
   "type": "PACKAGE",
   "url": "https://huggingface.co/unsloth/Llama-3.2-1B-Instruct"
  },
  {
   "type": "WEB",
   "url": "https://www.neurarch.com/changes-feeds/models/unsloth/Llama-3.2-1B-Instruct.html"
  }
 ],
 "database_specific": {
  "source": "neurarch model change tracker",
  "model": "unsloth/Llama-3.2-1B-Instruct",
  "kind": "tokenizer",
  "classes": [
   "tokenizer",
   "template",
   "generation-defaults"
  ],
  "changed_keys": [
   {
    "file": "config",
    "key": "pad_token_id",
    "before": null,
    "after": 128004,
    "class": "tokenizer"
   },
   {
    "file": "tokenizer",
    "key": "add_bos_token",
    "before": null,
    "after": true,
    "class": "tokenizer"
   },
   {
    "file": "tokenizer",
    "key": "chat_template_sha256",
    "before": "5816fce10444e03c",
    "after": "053402b579e589c0",
    "class": "template"
   },
   {
    "file": "generation",
    "key": "max_length",
    "before": null,
    "after": 131072,
    "class": "generation-defaults"
   },
   {
    "file": "generation",
    "key": "pad_token_id",
    "before": null,
    "after": 128004,
    "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": "2025-01-22T09:38:08.000Z",
  "detected_at": "2026-10-18T09:00:52.565Z",
  "detected_by": "backfill",
  "days_since_first_commit": 118,
  "license": "CC-BY-4.0"
 }
}