cstr/pixie-rune-v1-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "mit",
    "language": [
      "multilingual"
    ],
    "tags": [
      "embeddings",
      "gguf",
      "ggml",
      "text-embeddings",
      "xlm-r",
      "crispembed",
      "ollama"
    ],
    "pipeline_tag": "feature-extraction",
    "base_model": "telepix/PIXIE-Rune-v1.0",
    "frontmatter": {
      "license": "mit",
      "language": "[multilingual]",
      "tags": "[embeddings, gguf, ggml, text-embeddings, xlm-r, crispembed, ollama]",
      "pipeline_tag": "feature-extraction",
      "base_model": "telepix/PIXIE-Rune-v1.0"
    },
    "hero_image_url": "",
    "summary": "GGUF format of telepix/PIXIE-Rune-v1.0 for use with CrispEmbed and Ollama.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: mit\nlanguage: [multilingual]\ntags: [embeddings, gguf, ggml, text-embeddings, xlm-r, crispembed, ollama]\npipeline_tag: feature-extraction\nbase_model: telepix/PIXIE-Rune-v1.0\n---\n\n# pixie-rune-v1 GGUF\n\nGGUF format of [telepix/PIXIE-Rune-v1.0](https://huggingface.co/telepix/PIXIE-Rune-v1.0) for use with [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) and [Ollama](https://ollama.com).\n\n## Files\n\n| File | Quantization | Size |\n|------|-------------|------|\n| [pixie-rune-v1-q4_k.gguf](https://huggingface.co/cstr/pixie-rune-v1-GGUF/resolve/main/pixie-rune-v1-q4_k.gguf) | Q4_K | 0 MB |\n| [pixie-rune-v1-q8_0.gguf](https://huggingface.co/cstr/pixie-rune-v1-GGUF/resolve/main/pixie-rune-v1-q8_0.gguf) | Q8_0 | 0 MB |\n| [pixie-rune-v1.gguf](https://huggingface.co/cstr/pixie-rune-v1-GGUF/resolve/main/pixie-rune-v1.gguf) | F32 | 0 MB |\n\n**Recommended:** Q8_0 for quality (cos vs HF: cross-lingual OK), Q4_K for size (cross-lingual OK).\n\n## Quick Start\n\n### CrispEmbed\n```bash\n./crispembed -m pixie-rune-v1 \"Hello world\"\n./crispembed-server -m pixie-rune-v1 --port 8080\n```\n\n### Ollama (with [CrispStrobe fork](https://github.com/CrispStrobe/ollama/tree/feat/xlmr-embedding))\n```bash\necho \"FROM pixie-rune-v1-q8_0.gguf\" > Modelfile\nollama create pixie-rune-v1 -f Modelfile\ncurl http://localhost:11434/api/embed -d '{\"model\":\"pixie-rune-v1\",\"input\":[\"Hello world\"]}'\n```\n\n### Python (CrispEmbed)\n```python\nfrom crispembed import CrispEmbed\nmodel = CrispEmbed(\"pixie-rune-v1-q8_0.gguf\")\nvectors = model.encode([\"Hello world\", \"Goodbye world\"])\n```\n\n## Model Details\n\n| Property | Value |\n|----------|-------|\n| Architecture | XLM-R |\n| Parameters | 560M |\n| Embedding Dimension | 1024 |\n| Layers | 24 |\n| Pooling | CLS |\n| Tokenizer | SentencePiece |\n| Language | multilingual |\n| Q8_0 vs HuggingFace | cross-lingual OK |\n| Q4_K vs HuggingFace | cross-lingual OK |\n\n## Server API\n\nCrispEmbed server supports four API dialects:\n- `POST /embed` -- native\n- `POST /v1/embeddings` -- OpenAI-compatible\n- `POST /api/embed` -- Ollama-compatible\n- `POST /api/embeddings` -- Ollama legacy\n\n## Credits\n\n- Original model: [telepix/PIXIE-Rune-v1.0](https://huggingface.co/telepix/PIXIE-Rune-v1.0)\n- Inference: [CrispEmbed](https://github.com/CrispStrobe/CrispEmbed) (MIT, ggml-based)\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "embeddings",
    "ggml",
    "text-embeddings",
    "xlm-r",
    "crispembed",
    "ollama",
    "feature-extraction",
    "multilingual",
    "base_model:telepix/PIXIE-Rune-v1.0",
    "base_model:quantized:telepix/PIXIE-Rune-v1.0",
    "license:mit",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 790,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-16T05:28:20.000Z",
  "created_at": "2026-04-15T03:33:10.000Z",
  "pipeline_tag": "feature-extraction",
  "library_name": ""
}

{
  "_id": "69df06f69d1f89727a616336",
  "id": "cstr/pixie-rune-v1-GGUF",
  "modelId": "cstr/pixie-rune-v1-GGUF",
  "sha": "2fb50bc3ecdab9a174c0e3108b65b7757c7c630e",
  "createdAt": "2026-04-15T03:33:10.000Z",
  "lastModified": "2026-04-16T05:28:20.000Z",
  "author": "cstr",
  "downloads": 790,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "feature-extraction",
  "library_name": "",
  "siblings_count": 5
}