cygnisai/cygnis-alpha-1.7b-v0.1-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "library_name": "transformers",
    "license": "apache-2.0",
    "language": [
      "en",
      "fr"
    ],
    "pipeline_tag": "text-generation",
    "base_model": "cygnisai/Cygnis-Alpha-1.7B-v0.1",
    "tags": [
      "llama-cpp",
      "gguf",
      "i1-quant",
      "sovereign-ai",
      "cygnis"
    ],
    "frontmatter": {
      "library_name": "transformers",
      "license": "apache-2.0",
      "language": [
        "en",
        "fr"
      ],
      "pipeline_tag": "text-generation",
      "base_model": "cygnisai/Cygnis-Alpha-1.7B-v0.1",
      "tags": [
        "llama-cpp",
        "gguf",
        "i1-quant",
        "sovereign-ai",
        "cygnis"
      ]
    },
    "hero_image_url": "https://huggingface.co/cygnisai/Cygnis-Alpha-1.7B-v0.1/resolve/main/Cygnis-Alpha-1.7B-v1.png",
    "summary": "Welcome to the centralized repository for quantized versions of **Cygnis Alpha 1.7B**. This repository hosts various optimized variants (GGUF) for local inference, ranging from ultra-compressed formats to high-fidelity versions. **Base Model:** cygnisai/Cygnis-Alpha-1.7B-v0.1 **Architecture:** Based on SmolLM2-1.7B (Llama-style) ---",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlibrary_name: transformers\nlicense: apache-2.0\nlanguage:\n- en\n- fr\npipeline_tag: text-generation\nbase_model: cygnisai/Cygnis-Alpha-1.7B-v0.1\ntags:\n- llama-cpp\n- gguf\n- i1-quant\n- sovereign-ai\n- cygnis\n---\n\n# Cygnis Alpha 1.7B - GGUF Collection (i1 & imat)\n\n<div align=\"center\" style=\"background:#06090f; border-radius:14px; border:1px solid #0f1e30; overflow:hidden; margin-bottom:20px;\">\n  <img src=\"https://huggingface.co/cygnisai/Cygnis-Alpha-1.7B-v0.1/resolve/main/Cygnis-Alpha-1.7B-v1.png\" width=\"100%\" style=\"display:block;\">\n</div>\n\nWelcome to the centralized repository for quantized versions of **Cygnis Alpha 1.7B**. This repository hosts various optimized variants (GGUF) for local inference, ranging from ultra-compressed formats to high-fidelity versions.\n\n**Base Model:** [`cygnisai/Cygnis-Alpha-1.7B-v0.1`](https://huggingface.co/cygnisai/Cygnis-Alpha-1.7B-v0.1)  \n**Architecture:** Based on SmolLM2-1.7B (Llama-style)\n\n---\n\n## Quantization Table\n\nAll files below include an **Importance Matrix (imatrix)** to significantly improve coherence and reasoning at lower bitrates.\n\n| File (.gguf) | Method | Size | Best For |\n| :--- | :--- | :--- | :--- |\n| `cygnis-alpha-1.7b-v0.1-q5_k_m-imat.gguf` | Q5_K_M | 1.23 GB | **Recommended** - High precision |\n| `cygnis-alpha-1.7b-v0.1-q5_k_s-imat.gguf` | Q5_K_S | 1.18 GB | Great balance of speed/quality |\n| `cygnis-alpha-1.7b-v0.1-q4_k_m-imat.gguf` | Q4_K_M | 1.06 GB | Standard usage |\n| `cygnis-alpha-1.7b-v0.1-q4_k_s-imat.gguf` | Q4_K_S | 999 MB | Fits easily in 1GB VRAM/RAM |\n| `cygnis-alpha-1.7b-v0.1-iq4_nl-imat.gguf` | IQ4_NL | 991 MB | Optimized 4-bit coherence |\n| `cygnis-alpha-1.7b-v0.1-iq4_xs-imat.gguf` | IQ4_XS | 940 MB | Lean 4-bit performance |\n| `cygnis-alpha-1.7b-v0.1-iq3_m-imat.gguf` | IQ3_M | 810 MB | Significant compression |\n| `cygnis-alpha-1.7b-v0.1-iq3_xxs-imat.gguf` | IQ3_XXS | 680 MB | Extreme light-weight usage |\n\n---\n\n## Quick Start\n\n### With Ollama\nYou can use these models by creating a `Modelfile`:\n```dockerfile\nFROM ./cygnis-alpha-1.7b-v0.1-q5_k_m-imat.gguf\nPARAMETER temperature 0.7\nSYSTEM \"You are Cygnis Alpha, a sovereign AI designed by Simonc-44. You are polite, fast, and concise.\"\n```\n\n### With llama.cpp (CLI)\n```bash\n./llama-cli --hf-repo cygnisai/Cygnis-Alpha-1.7B-v0.1-i1-GGUF \\\n            --hf-file cygnis-alpha-1.7b-v0.1-q5_k_m-imat.gguf \\\n            -p \"Hello Cygnis, introduce yourself.\"\n```\n\n---\n\n## About Cygnis Alpha\nCygnis Alpha is a **Sovereign AI** developed by **Simonc-44**. It has been fine-tuned via SFT (Supervised Fine-Tuning) for:\n1. **Identity Alignment**: It is fully aware of its origin and creator.\n2. **Conciseness**: Designed for fast, direct, and helpful responses.\n3. **Efficiency**: Operates on almost any hardware due to its compact 1.7B parameter count.\n\n## License\nThis project is distributed under the **Apache-2.0** license. Quantizations were performed using [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo).\n\n## Citation\n```bibtex\n@misc{allal2025smollm2smolgoesbig,\n      title={SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model}, \n      author={Loubna Ben Allal and others},\n      year={2025},\n      eprint={2502.02737},\n      archivePrefix={arXiv},\n}\n```\n---\n**Contact & Creator:** [Simonc-44](https://huggingface.co/Simonc-44)",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "llama-cpp",
    "i1-quant",
    "sovereign-ai",
    "cygnis",
    "text-generation",
    "en",
    "fr",
    "arxiv:2502.02737",
    "base_model:cygnisai/Cygnis-Alpha-1.7B-v0.1",
    "base_model:quantized:cygnisai/Cygnis-Alpha-1.7B-v0.1",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 1,
  "downloads": 704,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-29T11:19:45.000Z",
  "created_at": "2026-03-29T09:28:54.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "69c8f0d60b89aef2a258cf39",
  "id": "cygnisai/Cygnis-Alpha-1.7B-v0.1-i1-GGUF",
  "modelId": "cygnisai/Cygnis-Alpha-1.7B-v0.1-i1-GGUF",
  "sha": "839dce08ee6c2fc6258e73139342c45838530213",
  "createdAt": "2026-03-29T09:28:54.000Z",
  "lastModified": "2026-03-29T11:19:45.000Z",
  "author": "cygnisai",
  "downloads": 704,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 10
}