lewdiculous/layris_9b-gguf-iq-imatrix overview

{
  "metadata": {},
  "card_data": {
    "library_name": "transformers",
    "tags": [
      "mistral",
      "quantized",
      "text-generation-inference",
      "roleplay"
    ],
    "pipeline_tag": "text-generation",
    "inference": false,
    "frontmatter": {
      "library_name": "transformers",
      "tags": [
        "mistral",
        "quantized",
        "text-generation-inference",
        "roleplay"
      ],
      "pipeline_tag": "text-generation",
      "inference": "false"
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/aK81BYLc8LzspT5h68hET.jpeg",
    "summary": "!image/jpeg This is a merge of pre-trained language models created using mergekit.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlibrary_name: transformers\ntags:\n- mistral\n- quantized\n- text-generation-inference\n- roleplay\n# - rp\n# - uncensored\npipeline_tag: text-generation\ninference: false\n# language:\n# - en\n# FILL THE INFORMATION:\n# Reference: ChaoticNeutrals/Layris_9B\n# Author: ChaoticNeutrals\n# Model: Layris_9B\n# Llama.cpp version: b2350\n---\n\n> [!TIP]\n> **Support:** <br>\n> My upload speeds have been cooked and unstable lately. <br>\n> Realistically I'd need to move to get a better provider. <br>\n> If you **want** and you are able to... <br>\n> [**You can support my various endeavors here (Ko-fi).**](https://ko-fi.com/Lewdiculous) <br>\n> I apologize for disrupting your experience.\n\n\n```python\n    quantization_options = [\n        \"Q4_K_M\", \"Q4_K_S\", \"IQ4_XS\", \"Q5_K_M\", \n        \"Q5_K_S\", \"Q6_K\", \"Q8_0\", \"IQ3_M\", \"IQ3_S\", \"IQ3_XS\", \"IQ3_XXS\"\n    ]\n```\n\n## GGUF-Imatrix quantizations for [ChaoticNeutrals/Layris_9B](https://huggingface.co/ChaoticNeutrals/Layris_9B/).\n\nAll credits belong to the author.\n\nIf you liked these, check out the work with [FantasiaFoundry's GGUF-IQ-Imatrix-Quantization-Script](https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script).\n\n**Personal note:**\n\nThis model should give you less refusals, given it's merged with the unhinged **Layla-V4**.\n\n## What does \"Imatrix\" mean?\n\nIt stands for **Importance Matrix**, a technique used to improve the quality of quantized models. <br>\n[[1]](https://github.com/ggerganov/llama.cpp/discussions/5006/) <br>\nThe **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 and lead to better quality preservation, especially when the calibration data is diverse. <br>\n[[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384/)\n\nFor --imatrix data, included `imatrix.dat` was used.\n\nUsing [llama.cpp-b2350](https://github.com/ggerganov/llama.cpp/releases/tag/b2350/):\n\n```\nBase⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)\n```\n\nThe new **IQ3_S** quant-option has shown to be better than the old Q3_K_S, so I added that instead of the later. Only supported in `koboldcpp-1.59.1` or higher.\n\nIf you want any specific quantization to be added, feel free to ask.\n\n## Model card:\n\n![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/aK81BYLc8LzspT5h68hET.jpeg)\n\n## Original model information:\n\n# Layris\n\n![image/jpeg](https://i.imgur.com/yRGzsoO.jpeg)\n\nThis is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).\n\n## Merge Details\n### Merge Method\n\nThis model was merged using the passthrough merge method.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [ChaoticNeutrals/Eris_Remix_7B](https://huggingface.co/ChaoticNeutrals/Eris_Remix_7B)\n* [l3utterfly/mistral-7b-v0.1-layla-v4](https://huggingface.co/l3utterfly/mistral-7b-v0.1-layla-v4)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nslices:\n  - sources:\n      - model: ChaoticNeutrals/Eris_Remix_7B\n        layer_range: [0, 20]\n  - sources:\n      - model: l3utterfly/mistral-7b-v0.1-layla-v4\n        layer_range: [12, 32]\nmerge_method: passthrough\ndtype: float16\n```\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "mistral",
    "quantized",
    "text-generation-inference",
    "roleplay",
    "text-generation",
    "region:us"
  ],
  "likes": 20,
  "downloads": 272,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-04T14:46:07.000Z",
  "created_at": "2024-03-06T03:26:55.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "65e7e27fa620567af0f37f85",
  "id": "Lewdiculous/Layris_9B-GGUF-IQ-Imatrix",
  "modelId": "Lewdiculous/Layris_9B-GGUF-IQ-Imatrix",
  "sha": "147cd41f2187384014435090ff5e1414698cdd6b",
  "createdAt": "2024-03-06T03:26:55.000Z",
  "lastModified": "2024-05-04T14:46:07.000Z",
  "author": "Lewdiculous",
  "downloads": 272,
  "likes": 20,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 15
}