sanjiwatsuki/loyal-toppy-bruins-maid-7b-dare-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "cc-by-nc-4.0",
    "tags": [
      "merge"
    ],
    "frontmatter": {
      "license": "cc-by-nc-4.0",
      "tags": [
        "merge"
      ]
    },
    "hero_image_url": "https://huggingface.co/SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE/resolve/main/bruins-maid.png",
    "summary": "!image/png",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: cc-by-nc-4.0\ntags:\n- merge\n---\n\n![image/png](https://huggingface.co/SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE/resolve/main/bruins-maid.png)\n\n<!-- description start -->\n## Description\n\nThis repository hosts quantized GGUF files for **Loyal-Toppy-Bruins-Maid-7B**, a 7B model aimed at having engaging RP with solid character card adherence and being a smart cookie at the same time.\n\nIts foundation is [Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha), notable for its performance in the LMSYS Chatbot Arena, even surpassing GPT-3.5-Turbo-1106. The model incorporates [rwitz/go-bruins-v2](https://huggingface.co/rwitz/go-bruins-v2), a [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling) derivative with Alpaca RP data tuning.\n\nThe other foundational model is [chargoddard/loyal-piano-m7](https://huggingface.co/chargoddard/loyal-piano-m7), chosen for its strong RP performance and Alpaca format training, with a diverse dataset including PIPPA, rpbuild, and LimaRP.\n\n[Undi95/Toppy-M-7B](https://huggingface.co/Undi95/Toppy-M-7B), known for its creativity, brings in useful RP data from various sources. It ranks first among 7B models on [OpenRouter](https://openrouter.ai/rankings) for a good reason.\n\n[NeverSleep/Noromaid-7b-v0.1.1](https://huggingface.co/NeverSleep/Noromaid-7b-v0.1.1), a Mistral finetune with unique RP data not present in other models, was also added for bringing in a unique RP dataset and being a well-regarded RP model.\n\nThe models were merged using the DARE ties method, with a targeted 1.2 absolute weight and high density (0.5-0.6), as discussed in the [MergeKit GitHub Repo](https://github.com/cg123/mergekit/issues/26).\n\nCurrently, this model ranks at the top of my personal RP unit test benchmark and scored a very solid 20 on [lilblam's LLM Logic Test](https://docs.google.com/spreadsheets/d/1NgHDxbVWJFolq8bLvLkuPWKC7i_R6I6W/edit#gid=1278290632). My first impressions of it for RPing are very good but, admittedly, this model came out of the oven today so I haven't played it with it too much 😊\n\n### The sauce\n```\nmodels: # Top-Loyal-Bruins-Maid-DARE-7B_v2\n  - model: mistralai/Mistral-7B-v0.1\n    # no parameters necessary for base model\n  - model: rwitz/go-bruins-v2 # MetamathCybertronStarling base\n    parameters:\n      weight: 0.5\n      density: 0.6\n  - model: chargoddard/loyal-piano-m7 # Pull in some PIPPA/LimaRP/Orca/rpguild\n    parameters:\n      weight: 0.5\n      density: 0.6\n  - model: Undi95/Toppy-M-7B\n    parameters:\n      weight: 0.1\n      density: 0.5\n  - model: NeverSleep/Noromaid-7b-v0.1.1\n    parameters:\n      weight: 0.1\n      density: 0.5\nmerge_method: dare_ties\nbase_model: mistralai/Mistral-7B-v0.1\nparameters:\n  normalize: false\n  int8_mask: true\ndtype: bfloat16\n```\n\n<!-- description end -->\n<!-- prompt-template start -->\n## Prompt template: Custom format, or Alpaca\n\n### Custom format:\nI found the best SillyTavern results from using the Noromaid template.\n\nSillyTavern config files: [Context](https://files.catbox.moe/ifmhai.json), [Instruct](https://files.catbox.moe/ttw1l9.json).\n\nOtherwise, I tried to ensure that all of the underlying merged models were Alpaca favored.\n\n### Alpaca:\n```\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:\n\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "merge",
    "license:cc-by-nc-4.0",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 11,
  "downloads": 168,
  "gated": false,
  "private": false,
  "last_modified": "2023-12-21T09:59:33.000Z",
  "created_at": "2023-12-21T03:39:55.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6583b38b9c0bff91b139872e",
  "id": "SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE-GGUF",
  "modelId": "SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE-GGUF",
  "sha": "64125add168695a6874a55ae8b54679056ca4f3b",
  "createdAt": "2023-12-21T03:39:55.000Z",
  "lastModified": "2023-12-21T09:59:33.000Z",
  "author": "SanjiWatsuki",
  "downloads": 168,
  "likes": 11,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 8
}