mradermacher/stentor-30m-instruct-heretic-safety-defiltered-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "MihaiPopa-1/Stentor-30M-Instruct-heretic-safety-defiltered",
    "datasets": [
      "PKU-Alignment/BeaverTails",
      "AmazonScience/FalseReject",
      "databricks/databricks-dolly-15k"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "text-generation",
      "llama",
      "small-language-model",
      "efficient",
      "edge-deployment",
      "tiny-model",
      "30m-parameters",
      "safety-tuning",
      "instruction-following",
      "chat",
      "lora",
      "peft",
      "beavertails",
      "dolly",
      "heretic",
      "uncensored",
      "decensored",
      "abliterated",
      "defiltered",
      "safety-defiltered"
    ],
    "frontmatter": {
      "base_model": "MihaiPopa-1/Stentor-30M-Instruct-heretic-safety-defiltered",
      "datasets": [
        "PKU-Alignment/BeaverTails",
        "AmazonScience/FalseReject",
        "databricks/databricks-dolly-15k"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "text-generation",
        "llama",
        "small-language-model",
        "efficient",
        "edge-deployment",
        "tiny-model",
        "30m-parameters",
        "safety-tuning",
        "instruction-following",
        "chat",
        "lora",
        "peft",
        "beavertails",
        "dolly",
        "heretic",
        "uncensored",
        "decensored",
        "abliterated",
        "defiltered",
        "safety-defiltered"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/MihaiPopa-1/Stentor-30M-Instruct-heretic-safety-defiltered  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: MihaiPopa-1/Stentor-30M-Instruct-heretic-safety-defiltered\ndatasets:\n- PKU-Alignment/BeaverTails\n- AmazonScience/FalseReject\n- databricks/databricks-dolly-15k\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- text-generation\n- llama\n- small-language-model\n- efficient\n- edge-deployment\n- tiny-model\n- 30m-parameters\n- safety-tuning\n- instruction-following\n- chat\n- lora\n- peft\n- beavertails\n- dolly\n- heretic\n- uncensored\n- decensored\n- abliterated\n- defiltered\n- safety-defiltered\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags: nicoboss -->\n<!-- ### quants:  Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->\n<!-- ### quants_skip:  -->\n<!-- ### skip_mmproj:  -->\nweighted/imatrix quants of https://huggingface.co/MihaiPopa-1/Stentor-30M-Instruct-heretic-safety-defiltered\n\n<!-- provided-files -->\n\n***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-GGUF\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ1_S.gguf) | i1-IQ1_S | 0.1 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ1_M.gguf) | i1-IQ1_M | 0.1 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ2_S.gguf) | i1-IQ2_S | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ2_M.gguf) | i1-IQ2_M | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.1 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.1 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q2_K.gguf) | i1-Q2_K | 0.1 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ3_S.gguf) | i1-IQ3_S | 0.1 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.1 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ3_M.gguf) | i1-IQ3_M | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.1 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.1 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.1 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q4_0.gguf) | i1-Q4_0 | 0.1 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.1 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.1 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q4_1.gguf) | i1-Q4_1 | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF/resolve/main/Stentor-30M-Instruct-heretic-safety-defiltered.i1-Q6_K.gguf) | i1-Q6_K | 0.1 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "text-generation",
    "llama",
    "small-language-model",
    "efficient",
    "edge-deployment",
    "tiny-model",
    "30m-parameters",
    "safety-tuning",
    "instruction-following",
    "chat",
    "lora",
    "peft",
    "beavertails",
    "dolly",
    "heretic",
    "uncensored",
    "decensored",
    "abliterated",
    "defiltered",
    "safety-defiltered",
    "en",
    "dataset:PKU-Alignment/BeaverTails",
    "dataset:AmazonScience/FalseReject",
    "dataset:databricks/databricks-dolly-15k",
    "base_model:MihaiPopa-1/Stentor-30M-Instruct-heretic-safety-defiltered",
    "base_model:adapter:MihaiPopa-1/Stentor-30M-Instruct-heretic-safety-defiltered",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 1,
  "downloads": 1019,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-08T12:32:23.000Z",
  "created_at": "2026-04-08T11:12:33.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "69d638217e0be2332a6f330d",
  "id": "mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF",
  "modelId": "mradermacher/Stentor-30M-Instruct-heretic-safety-defiltered-i1-GGUF",
  "sha": "87f2dd22d5dd5ad473f79f1c12ee5627ccd07a45",
  "createdAt": "2026-04-08T11:12:33.000Z",
  "lastModified": "2026-04-08T12:32:23.000Z",
  "author": "mradermacher",
  "downloads": 1019,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 27
}