richarderkhov/awnr_-_mistral-7b-v0.1-signtensors-5-over-16-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "I'm experimenting with the weight matrices in neural networks. This is a clone of Mistral-7B-v0.1 with some weight matrices replaced. I'm interested in seeing how the adjustmenets affect performance on existing metrics.",
    "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\nMistral-7B-v0.1-signtensors-5-over-16 - GGUF\n- Model creator: https://huggingface.co/awnr/\n- Original model: https://huggingface.co/awnr/Mistral-7B-v0.1-signtensors-5-over-16/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q2_K.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q2_K.gguf) | Q2_K | 2.53GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.IQ3_S.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.IQ3_M.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q3_K.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q3_K.gguf) | Q3_K | 3.28GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q4_0.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.IQ4_NL.gguf) | IQ4_NL | 1.5GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q4_K_S.gguf) | Q4_K_S | 3.43GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q4_K.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q4_K.gguf) | Q4_K | 1.25GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q4_1.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q5_0.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q5_K.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q5_K.gguf) | Q5_K | 4.78GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q5_1.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q5_1.gguf) | Q5_1 | 4.66GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q6_K.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q6_K.gguf) | Q6_K | 5.53GB |\n| [Mistral-7B-v0.1-signtensors-5-over-16.Q8_0.gguf](https://huggingface.co/RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf/blob/main/Mistral-7B-v0.1-signtensors-5-over-16.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\nmodel-index:\n- name: Mistral-7B-v0.1-signtensors-5-over-16\n  results:\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: IFEval (0-Shot)\n      type: HuggingFaceH4/ifeval\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: inst_level_strict_acc and prompt_level_strict_acc\n      value: 21.18\n      name: strict accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: BBH (3-Shot)\n      type: BBH\n      args:\n        num_few_shot: 3\n    metrics:\n    - type: acc_norm\n      value: 17.54\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MATH Lvl 5 (4-Shot)\n      type: hendrycks/competition_math\n      args:\n        num_few_shot: 4\n    metrics:\n    - type: exact_match\n      value: 2.19\n      name: exact match\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: GPQA (0-shot)\n      type: Idavidrein/gpqa\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: acc_norm\n      value: 4.14\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MuSR (0-shot)\n      type: TAUR-Lab/MuSR\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: acc_norm\n      value: 6.14\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MMLU-PRO (5-shot)\n      type: TIGER-Lab/MMLU-Pro\n      config: main\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 21.75\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=awnr/Mistral-7B-v0.1-signtensors-5-over-16\n      name: Open LLM Leaderboard\n---\n\n# Model Card for Model Mistral-7B-v0.1-5-over-16\n\nI'm experimenting with the weight matrices in neural networks.\nThis is a clone of `Mistral-7B-v0.1` with some weight matrices replaced.\n\nI'm interested in seeing how the adjustmenets affect performance on existing metrics.\n\n## Model Details\n\nResearch in progress! Demons could come out of your nose if you use this.\n\n### Model Description\n\nA modification of [`mistralai/Mistral-7B-v0.1`](https://huggingface.co/mistralai/Mistral-7B-v0.1).\nThanks to their team for sharing their model.\n\n\n- **Modified by:** Dr. Alex W. Neal Riasanovsky\n- **Model type:** pre-trained\n- **Language(s) (NLP):** English\n- **License:** Apache-2.0\n\n## Bias, Risks, and Limitations\n\nUse your own risk.\nI have no idea what this model's biases and limitations are.\nI just want to see if the benchmark values are similar to those from `Mistral-7B-v0.1`.\nI am setting up a long computational experiment to test some ideas.\n\n# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_awnr__Mistral-7B-v0.1-signtensors-5-over-16)\n\n|      Metric       |Value|\n|-------------------|----:|\n|Avg.               |12.16|\n|IFEval (0-Shot)    |21.18|\n|BBH (3-Shot)       |17.54|\n|MATH Lvl 5 (4-Shot)| 2.19|\n|GPQA (0-shot)      | 4.14|\n|MuSR (0-shot)      | 6.14|\n|MMLU-PRO (5-shot)  |21.75|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 650,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-03T08:32:05.000Z",
  "created_at": "2024-08-03T06:29:25.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66adce4576044810f5e854c1",
  "id": "RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf",
  "modelId": "RichardErkhov/awnr_-_Mistral-7B-v0.1-signtensors-5-over-16-gguf",
  "sha": "a889d1568c903be499e4ce3970e9797874a14b41",
  "createdAt": "2024-08-03T06:29:25.000Z",
  "lastModified": "2024-08-03T08:32:05.000Z",
  "author": "RichardErkhov",
  "downloads": 650,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}