lewdiculous/eris-daturamix-7b-v2-gguf-iq-imatrix overview

{
  "metadata": {},
  "card_data": {
    "library_name": "transformers",
    "license": "other",
    "language": [
      "en"
    ],
    "tags": [
      "gguf",
      "quantized",
      "roleplay",
      "imatrix",
      "mistral",
      "merge"
    ],
    "inference": false,
    "base_model": [
      "ResplendentAI/Datura_7B",
      "ChaoticNeutrals/Eris_Floramix_DPO_7B"
    ],
    "frontmatter": {
      "library_name": "transformers",
      "license": "other",
      "language": [
        "en"
      ],
      "tags": [
        "gguf",
        "quantized",
        "roleplay",
        "imatrix",
        "mistral",
        "merge"
      ],
      "inference": "false",
      "base_model": [
        "ResplendentAI/Datura_7B",
        "ChaoticNeutrals/Eris_Floramix_DPO_7B"
      ]
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/reCtUSmNO6S1mSjLms3kT.png",
    "summary": "This repository hosts GGUF-Imatrix quantizations for Test157t/Eris-Daturamix-7b-v2. **What does \"Imatrix\" mean?** It stands for **Importance Matrix**, a technique used to improve the quality of quantized models. The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse. [[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) **Steps:** `` Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants) ` Quants: `python quantization_options = [ \"Q4_K_M\", \"IQ4_XS\", \"Q5_K_M\", \"Q5_K_S\", \"Q6_K\", \"Q8_0\", \"IQ3_M\", \"IQ3_S\", \"IQ3_XXS\" ] ` **This is experimental.** For imatrix data generation, kalomaze's groups_merged.txt with added roleplay chats was used, you can find it here. **Alt-img:** !image/png **Original model information:** So this should have been v1 but i done goofed, so heres \"v2\". !image/png The following models were included in the merge: * ResplendentAI/Datura_7B * ChaoticNeutrals/Eris_Floramix_DPO_7B ### Configuration The following YAML configuration was used to produce this model: `yaml slices: layer_range: [0, 32] layer_range: [0, 32] merge_method: slerp base_model: ChaoticNeutrals/Eris_Floramix_DPO_7B parameters: t: value: [0, 0.5, 0.3, 0.7, 1] value: [1, 0.5, 0.7, 0.3, 0] dtype: bfloat16 ``",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlibrary_name: transformers\nlicense: other\nlanguage:\n- en\ntags:\n- gguf\n- quantized\n- roleplay\n- imatrix\n- mistral\n- merge\ninference: false\nbase_model:\n- ResplendentAI/Datura_7B\n- ChaoticNeutrals/Eris_Floramix_DPO_7B\n---\n\nThis repository hosts GGUF-Imatrix quantizations for [Test157t/Eris-Daturamix-7b-v2](https://huggingface.co/Test157t/Eris-Daturamix-7b-v2).\n\n**What does \"Imatrix\" mean?**\n\nIt stands for **Importance Matrix**, a technique used to improve the quality of quantized models.\nThe **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process.\nThe idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse.\n[[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)\n\n**Steps:**\n```\nBase⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)\n```\nQuants:\n```python\n    quantization_options = [\n        \"Q4_K_M\", \"IQ4_XS\", \"Q5_K_M\", \"Q5_K_S\", \"Q6_K\",\n        \"Q8_0\", \"IQ3_M\", \"IQ3_S\", \"IQ3_XXS\"\n    ]\n```\n\n**This is experimental.**\n\nFor imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt).\n\n**Alt-img:**\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/reCtUSmNO6S1mSjLms3kT.png)\n\n**Original model information:**\n\nSo this should have been v1 but i done goofed, so heres \"v2\".\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/O8bRFd7O9TDgecUy-mIWb.png)\n\nThe following models were included in the merge:\n* [ResplendentAI/Datura_7B](https://huggingface.co/ResplendentAI/Datura_7B)\n* [ChaoticNeutrals/Eris_Floramix_DPO_7B](https://huggingface.co/ChaoticNeutrals/Eris_Floramix_DPO_7B)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nslices:\n  - sources:\n      - model: ChaoticNeutrals/Eris_Floramix_DPO_7B\n        layer_range: [0, 32]\n      - model: ResplendentAI/Datura_7B\n        layer_range: [0, 32]\nmerge_method: slerp\nbase_model: ChaoticNeutrals/Eris_Floramix_DPO_7B\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",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "quantized",
    "roleplay",
    "imatrix",
    "mistral",
    "merge",
    "en",
    "base_model:ChaoticNeutrals/Eris_Floramix_DPO_7B",
    "base_model:merge:ChaoticNeutrals/Eris_Floramix_DPO_7B",
    "base_model:ResplendentAI/Datura_7B",
    "base_model:merge:ResplendentAI/Datura_7B",
    "license:other",
    "region:us"
  ],
  "likes": 6,
  "downloads": 124,
  "gated": false,
  "private": false,
  "last_modified": "2024-03-11T12:02:36.000Z",
  "created_at": "2024-03-09T00:52:46.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "65ebb2de563dc23bcc34fd01",
  "id": "Lewdiculous/Eris-Daturamix-7b-v2-GGUF-IQ-Imatrix",
  "modelId": "Lewdiculous/Eris-Daturamix-7b-v2-GGUF-IQ-Imatrix",
  "sha": "81ba03e26f0b655637b17707347c6b17a1b6c6f4",
  "createdAt": "2024-03-09T00:52:46.000Z",
  "lastModified": "2024-03-11T12:02:36.000Z",
  "author": "Lewdiculous",
  "downloads": 124,
  "likes": 6,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 14
}