etemiz/ostrich-27b-qwen3.5-260305-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "base_model": [
      "Qwen/Qwen3.5-27B"
    ],
    "tags": [
      "#aha",
      "#health",
      "#nutrition",
      "#medicinalherbs",
      "#fasting",
      "#faith",
      "#healing",
      "#bitcoin",
      "#nostr"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "base_model": [
        "Qwen/Qwen3.5-27B"
      ],
      "tags": [
        "'#aha'",
        "'#health'",
        "'#nutrition'",
        "'#medicinalherbs'",
        "'#fasting'",
        "'#faith'",
        "'#healing'",
        "'#bitcoin'",
        "'#nostr'"
      ]
    },
    "hero_image_url": "",
    "summary": "Ostrich LLMs, bringing you \"the knowledge that matters\". Methods used for fine tuning: Why: https://huggingface.co/blog/etemiz/building-a-beneficial-ai GSPO training made the thinking lengths shorter. I mainly targeted about 3000 letters (~1000 tokens) for thinking budget. Model is also abliterated since we built on @huihui-ai's model. We plan to release many more based on Qwen 3.5 27B. Comparison of some answers between another of our fine tune and base model: https://sheet.zohopublic.com/sheet/published/um332e3d15f34bfe64605ad3c1b149c9f8ca4 These answers are not from this model but it is a similar work. Thanks @unslothai for providing amazing tools. Sponsored by https://pickabrain.ai . A newer version of this runs there.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nbase_model:\n- Qwen/Qwen3.5-27B\ntags:\n- '#aha'\n- '#health'\n- '#nutrition'\n- '#medicinalherbs'\n- '#fasting'\n- '#faith'\n- '#healing'\n- '#bitcoin'\n- '#nostr'\n---\n\n# Ostrich 27B - Qwen 3.5 with Better Human Alignment\n\nOstrich LLMs, bringing you \"the knowledge that matters\".\n\n- Health, nutrition, medicinal herbs\n- Fasting, faith, healing\n- Liberating technologies like bitcoin and nostr\n\nMethods used for fine tuning:\n- CPT\n- SFT\n- GSPO\n\n\nWhy: https://huggingface.co/blog/etemiz/building-a-beneficial-ai\n\nGSPO training made the thinking lengths shorter. I mainly targeted about 3000 letters (~1000 tokens) for thinking budget.\n\nModel is also abliterated since we built on @huihui-ai's model.\n\nWe plan to release many more based on Qwen 3.5 27B. \n\nComparison of some answers between another of our fine tune and base model: https://sheet.zohopublic.com/sheet/published/um332e3d15f34bfe64605ad3c1b149c9f8ca4 These answers are not from this model but it is a similar work.\n\nThanks @unslothai for providing amazing tools.\n\nSponsored by https://pickabrain.ai . A newer version of this runs there.",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "#aha",
    "#health",
    "#nutrition",
    "#medicinalherbs",
    "#fasting",
    "#faith",
    "#healing",
    "#bitcoin",
    "#nostr",
    "base_model:Qwen/Qwen3.5-27B",
    "base_model:quantized:Qwen/Qwen3.5-27B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 706,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-31T19:11:51.000Z",
  "created_at": "2026-03-06T06:37:57.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69aa7645e6af9da1c56a845e",
  "id": "etemiz/Ostrich-27B-Qwen3.5-260305-GGUF",
  "modelId": "etemiz/Ostrich-27B-Qwen3.5-260305-GGUF",
  "sha": "1ca38453b7298f689b0eb96c10554cdb177af786",
  "createdAt": "2026-03-06T06:37:57.000Z",
  "lastModified": "2026-03-31T19:11:51.000Z",
  "author": "etemiz",
  "downloads": 706,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 9
}