lewdiculous/eris_primev3-vision-7b-gguf-iq-imatrix overview

{
  "metadata": {},
  "card_data": {
    "license": "other",
    "tags": [
      "gguf",
      "quantized",
      "roleplay",
      "multimodal",
      "vision",
      "sillytavern",
      "merge",
      "mistral"
    ],
    "frontmatter": {
      "license": "other",
      "tags": [
        "gguf",
        "quantized",
        "roleplay",
        "multimodal",
        "vision",
        "sillytavern",
        "merge",
        "mistral"
      ]
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/qGO0nIfZVcyuio5J07sU-.jpeg",
    "summary": "Click here to see how this would work in practice in a roleplay chat.  !image/jpeg   Click here to see what your SillyTavern Image Captions extension settings should look like.  !image/jpeg  **If you want to use vision functionality:** * Make sure you are using the latest version of KoboldCpp. To use the multimodal capabilities of this model, such as **vision**, you also need to load the specified **mmproj** file, you can get it here. * You can load the **mmproj** by using the corresponding section in the interface: !image/png * For CLI users, you can load the **mmproj file** by adding the respective flag to your usual command: `` --mmproj your-mmproj-file.gguf ` # Quantization information: **Steps performed:** ` Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants) ` *Using the latest llama.cpp at the time.* # Original model information: !image/png Eris with vision capabilites supported by KCPP (required for vision support): https://huggingface.co/koboldcpp/mmproj/blob/main/mistral-7b-mmproj-v1.5-Q4_1.gguf This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * InferenceIllusionist/Excalibur-7b * ChaoticNeutrals/Eris_Prime-V2-7B ### 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_Prime-V2-7B 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": "---\nlicense: other\ntags:\n- gguf\n- quantized\n- roleplay\n- multimodal\n- vision\n- sillytavern\n- merge\n- mistral\n---\nThis repository hosts GGUF-IQ-Imatrix quants for [ChaoticNeutrals/Eris_PrimeV3-Vision-7B](https://huggingface.co/ChaoticNeutrals/Eris_PrimeV3-Vision-7B).\n\nThis is a #multimodal model that also has vision capabilities. Read the full card information if that is your use case.\n\nQuants:\n```python\n    quantization_options = [\n        \"Q4_K_M\", \"Q4_K_S\", \"IQ4_XS\", \"Q5_K_M\", \"Q5_K_S\",\n        \"Q6_K\", \"Q8_0\", \"IQ3_M\", \"IQ3_S\", \"IQ3_XXS\"\n    ]\n```\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\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). This was just to add a bit more diversity to the data.\n\n# Vision/multimodal capabilities:\n\n<details><summary>\nClick here to see how this would work in practice in a roleplay chat.\n</summary>\n  \n![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/qGO0nIfZVcyuio5J07sU-.jpeg)\n  \n</details><br>\n\n<details><summary>\nClick here to see what your SillyTavern Image Captions extension settings should look like.\n</summary>\n  \n![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UpXOnVrzvsMRYeqMaSOaa.jpeg)\n  \n</details><br>\n\n**If you want to use vision functionality:**\n\n* Make sure you are using the latest version of [KoboldCpp](https://github.com/LostRuins/koboldcpp).\n\nTo use the multimodal capabilities of this model, such as **vision**, you also need to load the specified **mmproj** file, you can get it [here](https://huggingface.co/cjpais/llava-1.6-mistral-7b-gguf/blob/main/mmproj-model-f16.gguf).\n\n* You can load the **mmproj** by using the corresponding section in the interface:\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/UX6Ubss2EPNAT3SKGMLe0.png)\n\n* For CLI users, you can load the **mmproj file** by adding the respective flag to your usual command:\n\n```\n--mmproj your-mmproj-file.gguf\n```\n\n# Quantization information:\n\n**Steps performed:**\n\n```\nBase⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)\n```\n*Using the latest llama.cpp at the time.*\n\n# Original model information:\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/O6REGzkSHunCzXuxsSMn7.png)\n\nEris with vision capabilites supported by KCPP (required for vision support): https://huggingface.co/koboldcpp/mmproj/blob/main/mistral-7b-mmproj-v1.5-Q4_1.gguf\n\nThis model was merged using the SLERP merge method.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [InferenceIllusionist/Excalibur-7b](https://huggingface.co/InferenceIllusionist/Excalibur-7b)\n* [ChaoticNeutrals/Eris_Prime-V2-7B](https://huggingface.co/ChaoticNeutrals/Eris_Prime-V2-7B)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nslices:\n  - sources:\n      - model: ChaoticNeutrals/Eris_Prime-V2-7B\n        layer_range: [0, 32]\n      - model: InferenceIllusionist/Excalibur-7b\n        layer_range: [0, 32]\nmerge_method: slerp\nbase_model: ChaoticNeutrals/Eris_Prime-V2-7B\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```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "quantized",
    "roleplay",
    "multimodal",
    "vision",
    "sillytavern",
    "merge",
    "mistral",
    "license:other",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 14,
  "downloads": 150,
  "gated": false,
  "private": false,
  "last_modified": "2024-03-21T21:44:25.000Z",
  "created_at": "2024-03-21T05:17:55.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "65fbc30384ce3e8a3937de05",
  "id": "Lewdiculous/Eris_PrimeV3-Vision-7B-GGUF-IQ-Imatrix",
  "modelId": "Lewdiculous/Eris_PrimeV3-Vision-7B-GGUF-IQ-Imatrix",
  "sha": "04a6f74d027b50ca740f7076848e5b6d3a7284e4",
  "createdAt": "2024-03-21T05:17:55.000Z",
  "lastModified": "2024-03-21T21:44:25.000Z",
  "author": "Lewdiculous",
  "downloads": 150,
  "likes": 14,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 18
}