richarderkhov/saishf_-_neural-sovlish-devil-8b-l3-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This is a merge of pre-trained language models created using mergekit.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nNeural-SOVLish-Devil-8B-L3 - GGUF\n- Model creator: https://huggingface.co/saishf/\n- Original model: https://huggingface.co/saishf/Neural-SOVLish-Devil-8B-L3/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Neural-SOVLish-Devil-8B-L3.Q2_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q2_K.gguf) | Q2_K | 2.96GB |\n| [Neural-SOVLish-Devil-8B-L3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [Neural-SOVLish-Devil-8B-L3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [Neural-SOVLish-Devil-8B-L3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [Neural-SOVLish-Devil-8B-L3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [Neural-SOVLish-Devil-8B-L3.Q3_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q3_K.gguf) | Q3_K | 3.74GB |\n| [Neural-SOVLish-Devil-8B-L3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [Neural-SOVLish-Devil-8B-L3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [Neural-SOVLish-Devil-8B-L3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [Neural-SOVLish-Devil-8B-L3.Q4_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [Neural-SOVLish-Devil-8B-L3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [Neural-SOVLish-Devil-8B-L3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [Neural-SOVLish-Devil-8B-L3.Q4_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q4_K.gguf) | Q4_K | 4.58GB |\n| [Neural-SOVLish-Devil-8B-L3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [Neural-SOVLish-Devil-8B-L3.Q4_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [Neural-SOVLish-Devil-8B-L3.Q5_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [Neural-SOVLish-Devil-8B-L3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [Neural-SOVLish-Devil-8B-L3.Q5_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q5_K.gguf) | Q5_K | 5.34GB |\n| [Neural-SOVLish-Devil-8B-L3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [Neural-SOVLish-Devil-8B-L3.Q5_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [Neural-SOVLish-Devil-8B-L3.Q6_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q6_K.gguf) | Q6_K | 6.14GB |\n| [Neural-SOVLish-Devil-8B-L3.Q8_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf/blob/main/Neural-SOVLish-Devil-8B-L3.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlicense: cc-by-nc-4.0\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\nbase_model:\n- mlabonne/NeuralDaredevil-8B-abliterated\n- ResplendentAI/BlueMoon_Llama3\n- mlabonne/NeuralDaredevil-8B-abliterated\n- ResplendentAI/Smarts_Llama3\n- mlabonne/NeuralDaredevil-8B-abliterated\n- ResplendentAI/Luna_Llama3\n- mlabonne/NeuralDaredevil-8B-abliterated\n- ResplendentAI/Aura_Llama3\n- mlabonne/NeuralDaredevil-8B-abliterated\n- ResplendentAI/RP_Format_QuoteAsterisk_Llama3\n- mlabonne/NeuralDaredevil-8B-abliterated\nmodel-index:\n- name: Neural-SOVLish-Devil-8B-L3\n  results:\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: AI2 Reasoning Challenge (25-Shot)\n      type: ai2_arc\n      config: ARC-Challenge\n      split: test\n      args:\n        num_few_shot: 25\n    metrics:\n    - type: acc_norm\n      value: 69.11\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Neural-SOVLish-Devil-8B-L3\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: HellaSwag (10-Shot)\n      type: hellaswag\n      split: validation\n      args:\n        num_few_shot: 10\n    metrics:\n    - type: acc_norm\n      value: 84.77\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Neural-SOVLish-Devil-8B-L3\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MMLU (5-Shot)\n      type: cais/mmlu\n      config: all\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 69.02\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Neural-SOVLish-Devil-8B-L3\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: TruthfulQA (0-shot)\n      type: truthful_qa\n      config: multiple_choice\n      split: validation\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: mc2\n      value: 59.05\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Neural-SOVLish-Devil-8B-L3\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: Winogrande (5-shot)\n      type: winogrande\n      config: winogrande_xl\n      split: validation\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 78.3\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Neural-SOVLish-Devil-8B-L3\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: GSM8k (5-shot)\n      type: gsm8k\n      config: main\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 73.09\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Neural-SOVLish-Devil-8B-L3\n      name: Open LLM Leaderboard\n---\n# merge\n\nThis is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).\n\n## Merge Details\nThis is another \"SOVL\" style merge, this time using [mlabonne/NeuralDaredevil-8B-abliterated](https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated). \n\nDaredevil is the first abliterated model series i've tried that feels as smart as base llama-3-instruct while also being willing to give instructions to do all kinda of illegal things \n\nNeural daredevil is trained further on the original abliterated model, which should result in a better experience in most scenarios. (A bandaid for the damage abliteration causes)\n\nThis model should do well in rp, I'm yet to test it (waiting for gguf files @_@) \n### Merge Method\n\nThis model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mlabonne/NeuralDaredevil-8B-abliterated](https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated) as a base.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [mlabonne/NeuralDaredevil-8B-abliterated](https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated) + [ResplendentAI/BlueMoon_Llama3](https://huggingface.co/ResplendentAI/BlueMoon_Llama3)\n* [mlabonne/NeuralDaredevil-8B-abliterated](https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated) + [ResplendentAI/Smarts_Llama3](https://huggingface.co/ResplendentAI/Smarts_Llama3)\n* [mlabonne/NeuralDaredevil-8B-abliterated](https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated) + [ResplendentAI/Luna_Llama3](https://huggingface.co/ResplendentAI/Luna_Llama3)\n* [mlabonne/NeuralDaredevil-8B-abliterated](https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated) + [ResplendentAI/Aura_Llama3](https://huggingface.co/ResplendentAI/Aura_Llama3)\n* [mlabonne/NeuralDaredevil-8B-abliterated](https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated) + [ResplendentAI/RP_Format_QuoteAsterisk_Llama3](https://huggingface.co/ResplendentAI/RP_Format_QuoteAsterisk_Llama3)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nmodels:\n  - model: mlabonne/NeuralDaredevil-8B-abliterated+ResplendentAI/Aura_Llama3\n  - model: mlabonne/NeuralDaredevil-8B-abliterated+ResplendentAI/Smarts_Llama3\n  - model: mlabonne/NeuralDaredevil-8B-abliterated+ResplendentAI/Luna_Llama3\n  - model: mlabonne/NeuralDaredevil-8B-abliterated+ResplendentAI/BlueMoon_Llama3\n  - model: mlabonne/NeuralDaredevil-8B-abliterated+ResplendentAI/RP_Format_QuoteAsterisk_Llama3\nmerge_method: model_stock\nbase_model: mlabonne/NeuralDaredevil-8B-abliterated\ndtype: bfloat16\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_saishf__Neural-SOVLish-Devil-8B-L3)\n\n|             Metric              |Value|\n|---------------------------------|----:|\n|Avg.                             |72.22|\n|AI2 Reasoning Challenge (25-Shot)|69.11|\n|HellaSwag (10-Shot)              |84.77|\n|MMLU (5-Shot)                    |69.02|\n|TruthfulQA (0-shot)              |59.05|\n|Winogrande (5-shot)              |78.30|\n|GSM8k (5-shot)                   |73.09|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2403.19522",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 115,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-09T10:15:32.000Z",
  "created_at": "2024-10-09T07:24:08.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67062f98e4b3f46ee8b24344",
  "id": "RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf",
  "modelId": "RichardErkhov/saishf_-_Neural-SOVLish-Devil-8B-L3-gguf",
  "sha": "a90c4cedb1b931a9603de9a3220c1ba66f6fafce",
  "createdAt": "2024-10-09T07:24:08.000Z",
  "lastModified": "2024-10-09T10:15:32.000Z",
  "author": "RichardErkhov",
  "downloads": 115,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}