richarderkhov/msl7_-_inex12-7b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "INEX12-7b is a merge of the following models using mergekit: * liminerity/merge2 * yam-peleg/Experiment26-7B",
    "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\nINEX12-7b - GGUF\n- Model creator: https://huggingface.co/MSL7/\n- Original model: https://huggingface.co/MSL7/INEX12-7b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [INEX12-7b.Q2_K.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q2_K.gguf) | Q2_K | 2.53GB |\n| [INEX12-7b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [INEX12-7b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [INEX12-7b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [INEX12-7b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [INEX12-7b.Q3_K.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q3_K.gguf) | Q3_K | 3.28GB |\n| [INEX12-7b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [INEX12-7b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [INEX12-7b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [INEX12-7b.Q4_0.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [INEX12-7b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [INEX12-7b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [INEX12-7b.Q4_K.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q4_K.gguf) | Q4_K | 4.07GB |\n| [INEX12-7b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [INEX12-7b.Q4_1.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [INEX12-7b.Q5_0.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [INEX12-7b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [INEX12-7b.Q5_K.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q5_K.gguf) | Q5_K | 4.78GB |\n| [INEX12-7b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [INEX12-7b.Q5_1.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [INEX12-7b.Q6_K.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q6_K.gguf) | Q6_K | 5.53GB |\n| [INEX12-7b.Q8_0.gguf](https://huggingface.co/RichardErkhov/MSL7_-_INEX12-7b-gguf/blob/main/INEX12-7b.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\ntags:\n- merge\n- mergekit\n- lazymergekit\n- liminerity/merge2\n- yam-peleg/Experiment26-7B\n---\n\n# INEX12-7b\n\nINEX12-7b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):\n* [liminerity/merge2](https://huggingface.co/liminerity/merge2)\n* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)\n\n## 🧩 Configuration\n\n```yaml\nslices:\n  - sources:\n      - model: liminerity/merge2\n        layer_range: [0, 32]\n      - model: yam-peleg/Experiment26-7B\n        layer_range: [0, 32]\nmerge_method: slerp\nbase_model: liminerity/merge2\nparameters:\n  t:\n    - filter: self_attn\n      value: [0, 0.5, 0.3, 0.7, 1]\n    - filter: mlp\n      value: [1, 0.5, 0.7, 0.3, 0]\n    - value: 0.5\ndtype: bfloat16\n\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 91,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-10T22:42:38.000Z",
  "created_at": "2024-09-10T16:48:35.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66e0786323e5f162e7fd6e3a",
  "id": "RichardErkhov/MSL7_-_INEX12-7b-gguf",
  "modelId": "RichardErkhov/MSL7_-_INEX12-7b-gguf",
  "sha": "c82a0deb2b0f4542f2194037e7d11a7dfc1afe8a",
  "createdAt": "2024-09-10T16:48:35.000Z",
  "lastModified": "2024-09-10T22:42:38.000Z",
  "author": "RichardErkhov",
  "downloads": 91,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}