epiculous/violet_twilight-v0.1-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "datasets": [
      "Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned",
      "Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned"
    ],
    "language": [
      "en",
      "fr",
      "de",
      "es",
      "it",
      "pt",
      "ru",
      "zh",
      "ja"
    ],
    "pipeline_tag": "text-generation",
    "tags": [
      "merge"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "datasets": [
        "Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned",
        "Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned"
      ],
      "language": [
        "en",
        "fr",
        "de",
        "es",
        "it",
        "pt",
        "ru",
        "zh",
        "ja"
      ],
      "pipeline_tag": "text-generation",
      "tags": [
        "merge"
      ]
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/64adfd277b5ff762771e4571/oTCM28M_Hu6lM4DmOp7tC.png",
    "summary": "full / exl2 / gguf",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\ndatasets:\n- Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned\n- Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned\nlanguage:\n- en\n- fr\n- de\n- es\n- it\n- pt\n- ru\n- zh\n- ja\npipeline_tag: text-generation\ntags:\n- merge\n---\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64adfd277b5ff762771e4571/oTCM28M_Hu6lM4DmOp7tC.png)\n\nNow for something a bit different, Violet_Twilight! This model is a SLERP merge of Azure_Dusk and Crimson_Dawn!\n\n# Quants!\n[full](https://huggingface.co/Epiculous/Violet_Twilight-v0.1) / [exl2](https://huggingface.co/Epiculous/Violet_Twilight-v0.1-Exl2) / <strong>gguf</strong>\n\n## Prompting\nViolet_Twilight's models were trained with the Mistral Instruct template, therefore it should be prompted in a similar way that you would prompt any other mistral based model.\n\n```\n\"<s>[INST] Prompt goes here [/INST]<\\s>\"\n```\n### Context and Instruct\n[Magnum-123B-Context.json](https://files.catbox.moe/rkyqwg.json) <br/>\n[Magnum-123B-Instruct.json](https://files.catbox.moe/obb5oe.json) <br/>\n*** NOTE *** <br/>\nThere have been reports of the quantized model misbehaving with the mistral prompt, if you are seeing issues it may be worth trying ChatML Context and Instruct templates.\nIf you are using GGUF I strongly advise using ChatML, for some reason that quantization performs better using ChatML.\n### Current Top Sampler Settings\n[Violet_Twilight-Nitral-Special](https://files.catbox.moe/ot54u3.json)- Considered the best settings! <br/>\n[Crimson_Dawn-Nitral-Special](https://files.catbox.moe/8xjxht.json) <br/>\n[Crimson_Dawn-Magnum-Style](https://files.catbox.moe/lc59dn.json) \n### Tokenizer\nIf you are using SillyTavern, please set the tokenizer to API (WebUI/ koboldcpp)\n\n## Merging\nThe following config was used to merge Azure Dusk and Crimson Dawn\n```yaml\nslices:\n  - sources:\n      - model: Epiculous/Azure_Dusk-v0.1\n        layer_range: [0, 40]\n      - model: Epiculous/Crimson_Dawn-V0.1\n        layer_range: [0, 40]\nmerge_method: slerp\nbase_model: Epiculous/Azure_Dusk-v0.1\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 # fallback for rest of tensors\ndtype: bfloat16\n\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "merge",
    "text-generation",
    "en",
    "fr",
    "de",
    "es",
    "it",
    "pt",
    "ru",
    "zh",
    "ja",
    "dataset:Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned",
    "dataset:Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 5,
  "downloads": 82,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-24T14:52:47.000Z",
  "created_at": "2024-08-23T02:26:13.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "66c7f3456058eb4e6b95fd72",
  "id": "Epiculous/Violet_Twilight-v0.1-GGUF",
  "modelId": "Epiculous/Violet_Twilight-v0.1-GGUF",
  "sha": "596ce1c106bf1a69083ecee3793c00b28ebdbc8c",
  "createdAt": "2024-08-23T02:26:13.000Z",
  "lastModified": "2024-08-24T14:52:47.000Z",
  "author": "Epiculous",
  "downloads": 82,
  "likes": 5,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 17
}