duyntnet/blurdus-7b-v0.1-imatrix-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "other",
    "language": [
      "en"
    ],
    "pipeline_tag": "text-generation",
    "inference": false,
    "tags": [
      "transformers",
      "gguf",
      "imatrix",
      "Blurdus-7b-v0.1"
    ],
    "frontmatter": {
      "license": "other",
      "language": [
        "en"
      ],
      "pipeline_tag": "text-generation",
      "inference": "false",
      "tags": [
        "transformers",
        "gguf",
        "imatrix",
        "Blurdus-7b-v0.1"
      ]
    },
    "hero_image_url": "",
    "summary": "Blurdus-7b-v0.1 is a merge of the following models using LazyMergekit: * 222gate/Blurred-Beagle-7b-slerp * 222gate/BrurryDog-7b-v0.1 * liminerity/Blur-7b-v1.21",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\nlanguage:\n- en\npipeline_tag: text-generation\ninference: false\ntags:\n- transformers\n- gguf\n- imatrix\n- Blurdus-7b-v0.1\n---\n\nQuantizations of https://huggingface.co/gate369/Blurdus-7b-v0.1\n\n\n### Open source inference clients/UIs\n* [llama.cpp](https://github.com/ggerganov/llama.cpp)\n* [KoboldCPP](https://github.com/LostRuins/koboldcpp)\n* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)\n* [jan](https://github.com/menloresearch/jan)\n* [ik_llama.cpp](https://github.com/ikawrakow/ik_llama.cpp)\n* [croco.cpp](https://github.com/Nexesenex/croco.cpp)\n\n### Closed source inference clients/UIs\n* [LM Studio](https://lmstudio.ai/)\n* More will be added...\n---\n\n# From original readme\n\nBlurdus-7b-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):\n* [222gate/Blurred-Beagle-7b-slerp](https://huggingface.co/222gate/Blurred-Beagle-7b-slerp)\n* [222gate/BrurryDog-7b-v0.1](https://huggingface.co/222gate/BrurryDog-7b-v0.1)\n* [liminerity/Blur-7b-v1.21](https://huggingface.co/liminerity/Blur-7b-v1.21)\n\n## 🧩 Configuration\n\n```yaml\nmodels:\n  - model: 222gate/Blurred-Beagle-7b-slerp\n    parameters:\n      density: [1, 0.7, 0.1] # density gradient\n      weight: 1.0\n  - model: 222gate/BrurryDog-7b-v0.1\n    parameters:\n      density: 0.5\n      weight: [0, 0.3, 0.7, 1] # weight gradient\n  - model: liminerity/Blur-7b-v1.21\n    parameters:\n      density: 0.33\n      weight:\n        - filter: mlp\n          value: 0.5\n        - value: 0\nmerge_method: ties\nbase_model: udkai/Turdus\nparameters:\n  normalize: true\n  int8_mask: true\ndtype: float16\n```\n\n## 💻 Usage\n\n```python\n!pip install -qU transformers accelerate\n\nfrom transformers import AutoTokenizer\nimport transformers\nimport torch\n\nmodel = \"222gate/Blurdus-7b-v0.1\"\nmessages = [{\"role\": \"user\", \"content\": \"What is a large language model?\"}]\n\ntokenizer = AutoTokenizer.from_pretrained(model)\nprompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\npipeline = transformers.pipeline(\n    \"text-generation\",\n    model=model,\n    torch_dtype=torch.float16,\n    device_map=\"auto\",\n)\n\noutputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)\nprint(outputs[0][\"generated_text\"])\n```\n# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_222gate__Blurdus-7b-v0.1)\n\n|             Metric              |Value|\n|---------------------------------|----:|\n|Avg.                             |74.35|\n|AI2 Reasoning Challenge (25-Shot)|72.27|\n|HellaSwag (10-Shot)              |88.50|\n|MMLU (5-Shot)                    |64.82|\n|TruthfulQA (0-shot)              |69.72|\n|Winogrande (5-shot)              |82.95|\n|GSM8k (5-shot)                   |67.85|",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "imatrix",
    "Blurdus-7b-v0.1",
    "text-generation",
    "en",
    "license:other",
    "region:us"
  ],
  "likes": 0,
  "downloads": 200,
  "gated": false,
  "private": false,
  "last_modified": "2025-09-27T08:14:50.000Z",
  "created_at": "2025-09-27T07:24:04.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "68d79114f12e2a0bdd747f49",
  "id": "duyntnet/Blurdus-7b-v0.1-imatrix-GGUF",
  "modelId": "duyntnet/Blurdus-7b-v0.1-imatrix-GGUF",
  "sha": "bb63a7ce14656df5d2606f8b526080283fae7fee",
  "createdAt": "2025-09-27T07:24:04.000Z",
  "lastModified": "2025-09-27T08:14:50.000Z",
  "author": "duyntnet",
  "downloads": 200,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 29
}