liquidai/lfm2-350m-pii-extract-jp-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "other",
    "license_name": "lfm1.0",
    "license_link": "LICENSE",
    "tags": [
      "liquid",
      "lfm2",
      "edge"
    ],
    "base_model": [
      "LiquidAI/LFM2-350M-PII-Extract-JP"
    ],
    "frontmatter": {},
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png",
    "summary": "Based on LFM2-350M, this checkpoint is designed to **extract personally identifiable information (PII) from Japanese text and output it in JSON format.** The output can then be used to mask out sensitive information in contracts, emails, personal medical reports, insurance bills, etc. directly on-device. Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2-350M-PII-Extract-JP",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "\n---\nlicense: other\nlicense_name: lfm1.0\nlicense_link: LICENSE\ntags:\n- liquid\n- lfm2\n- edge\nbase_model:\n- LiquidAI/LFM2-350M-PII-Extract-JP\n---\n\n<center>\n<div style=\"text-align: center;\">\n  <img \n    src=\"https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png\" \n    alt=\"Liquid AI\"\n    style=\"width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;\"\n  />\n</div>\n<div style=\"display: flex; justify-content: center; gap: 0.5em;\">\n  <a href=\"https://playground.liquid.ai/chat\">\n<a href=\"https://playground.liquid.ai/\"><strong>Try LFM</strong></a> • <a href=\"https://docs.liquid.ai/lfm\"><strong>Documentation</strong></a> • <a href=\"https://leap.liquid.ai/\"><strong>LEAP</strong></a></a>\n</div>\n</center>\n\n# LFM2-350M-PII-Extract-JP-GGUF\n\nBased on [LFM2-350M](https://huggingface.co/LiquidAI/LFM2-350M), this checkpoint is designed to **extract personally identifiable information (PII) from Japanese text and output it in JSON format.**\nThe output can then be used to mask out sensitive information in contracts, emails, personal medical reports, insurance bills, etc. directly on-device.\n\nFind more details in the original model card: https://huggingface.co/LiquidAI/LFM2-350M-PII-Extract-JP\n\n## 🏃 How to run LFM2\n\nExample usage with [llama.cpp](https://github.com/ggml-org/llama.cpp):\n\n- Extract address, company/institution names, email addresses, human names, and phone numbers from Japanese text.\n  ```\n  llama-cli -hf LiquidAI/LFM2-350M-PII-Extract-JP-GGUF -st --temp 0.0 --json-schema {} --jinja\n  ```\n  \n- Specifying a particular quantization scheme (e.g. `Q8_0`):\n  ```\n  llama-cli -hf LiquidAI/LFM2-350M-PII-Extract-JP-GGUF:Q8_0 -st --temp 0.0 --json-schema {} --jinja\n  ```\n  Several quantization variants are available (`Q4_0`, `Q4_K_M`, `Q5_K_M`, `Q6_K`, `Q8_0`, and `F16`).\n  \n- Only extracting particular entities (e.g. only extract `address` and `company_name`):\n  ```\n  llama-cli -hf LiquidAI/LFM2-350M-PII-Extract-JP-GGUF -st --temp 0.0 --json-schema {} -sys \"Extract <address>, <company_name>\"\n  ```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "liquid",
    "lfm2",
    "edge",
    "base_model:LiquidAI/LFM2-350M-PII-Extract-JP",
    "base_model:quantized:LiquidAI/LFM2-350M-PII-Extract-JP",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 8,
  "downloads": 950,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-06T18:53:24.000Z",
  "created_at": "2025-09-30T07:19:05.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "68db84697046bcbdc87a5b7a",
  "id": "LiquidAI/LFM2-350M-PII-Extract-JP-GGUF",
  "modelId": "LiquidAI/LFM2-350M-PII-Extract-JP-GGUF",
  "sha": "1d7f62918d68de6b6085296b8c2a2222b72afa82",
  "createdAt": "2025-09-30T07:19:05.000Z",
  "lastModified": "2026-04-06T18:53:24.000Z",
  "author": "LiquidAI",
  "downloads": 950,
  "likes": 8,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 12
}