flexan/novacorp-shadowncensored-1b-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "NovaCorp/Shadowncensored-1B",
    "library_name": "transformers",
    "tags": [
      "mergekit",
      "merge"
    ],
    "frontmatter": {
      "base_model": "NovaCorp/Shadowncensored-1B",
      "library_name": "transformers",
      "tags": [
        "mergekit",
        "merge"
      ]
    },
    "hero_image_url": "",
    "summary": "These are the GGUF files for NovaCorp/Shadowncensored-1B.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: NovaCorp/Shadowncensored-1B\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\n\n---\n\n# GGUF Files for Shadowncensored-1B\n\nThese are the GGUF files for [NovaCorp/Shadowncensored-1B](https://huggingface.co/NovaCorp/Shadowncensored-1B).\n\n## Downloads\n\n| GGUF Link | Quantization | Description |\n| ---- | ----- | ----------- |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q2_K.gguf) | Q2_K | Lowest quality |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q3_K_S.gguf) | Q3_K_S |  |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.IQ3_S.gguf) | IQ3_S | Integer quant, preferable over Q3_K_S |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.IQ3_M.gguf) | IQ3_M | Integer quant |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q3_K_M.gguf) | Q3_K_M |  |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q3_K_L.gguf) | Q3_K_L |  |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.IQ4_XS.gguf) | IQ4_XS | Integer quant |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q4_K_S.gguf) | Q4_K_S | Fast with good performance |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q4_K_M.gguf) | Q4_K_M | **Recommended:** Perfect mix of speed and performance |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q5_K_S.gguf) | Q5_K_S |  |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q5_K_M.gguf) | Q5_K_M |  |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q6_K.gguf) | Q6_K | Very good quality |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.Q8_0.gguf) | Q8_0 | Best quality |\n| [Download](https://huggingface.co/Flexan/NovaCorp-Shadowncensored-1B-GGUF/resolve/main/Shadowncensored-1B.f16.gguf) | f16 | Full precision, don't bother; use a quant |\n\n## Note from Flexan\n\nI provide GGUFs and quantizations of publicly available models that do not have a GGUF equivalent available yet,\nusually for models **I deem interesting and wish to try out**.\n\nIf there are some quants missing that you'd like me to add, you may request one in the community tab.\nIf you want to request a public model to be converted, you can also request that in the community tab.\nIf you have questions regarding this model, please refer to [the original model repo](https://huggingface.co/NovaCorp/Shadowncensored-1B).\n\nYou can find more info about me and what I do [here](https://huggingface.co/Flexan/Flexan).\n\n# Shadowncensored-1B\n\nThis is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).\n\n## Merge Details\n### Merge Method\n\nThis model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [lunahr/gemma-3-1b-it-abliterated](https://huggingface.co/lunahr/gemma-3-1b-it-abliterated)\n* [Echo9Zulu/Shadows-Gemma-3-1B](https://huggingface.co/Echo9Zulu/Shadows-Gemma-3-1B)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\n\n\n# Umbrella Corporation Official Merge Protocol v3.2\n# Author: Dr. Novaciano\n# Objective: Test\n# PROJECT: Shadowncensored-3.2-1B\n\nmodels:\n  - model: lunahr/gemma-3-1b-it-abliterated  # Experimental viral strain neural imprint\n  - model: Echo9Zulu/Shadows-Gemma-3-1B      # Baseline cognitive template, \"safe mode\"\n\nmerge_method: slerp  # Spherical Linear Interpolation to preserve extreme viral traits smoothly\nbase_model: lunahr/gemma-3-1b-it-abliterated  # Anchor model for stable latent space\n\ndtype: bfloat16  # Memory-efficient precision, minimal loss in viral feature fidelity\n\nparameters:\n  t: 0.45\n  normalize: false\n  rescale: true\n  rescale_factor: 1.12\n  memory_efficient: true\n  low_cpu_mem_usage: true\n\nlayer_range:\n  - value: [4, 22]\n\ntie_word_embeddings: true\ntie_output_embeddings: true\n\n\n\n```",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "mergekit",
    "merge",
    "base_model:NovaCorp/Shadowncensored-1B",
    "base_model:quantized:NovaCorp/Shadowncensored-1B",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 777,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-16T10:30:13.000Z",
  "created_at": "2026-04-16T10:28:22.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "69e0b9c6980f88483554a4f2",
  "id": "Flexan/NovaCorp-Shadowncensored-1B-GGUF",
  "modelId": "Flexan/NovaCorp-Shadowncensored-1B-GGUF",
  "sha": "fc4bf360c5c82ccabfcde02be8195221a8cf20d6",
  "createdAt": "2026-04-16T10:28:22.000Z",
  "lastModified": "2026-04-16T10:30:13.000Z",
  "author": "Flexan",
  "downloads": 777,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 16
}