lewdiculous/llama-3-stheno-mahou-8b-gguf-iq-imatrix overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en"
    ],
    "inference": false,
    "tags": [
      "roleplay",
      "llama3",
      "sillytavern"
    ],
    "base_model": [
      "nbeerbower/llama-3-Stheno-Mahou-8B"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en"
      ],
      "inference": "false",
      "tags": [
        "roleplay",
        "llama3",
        "sillytavern"
      ],
      "base_model": [
        "nbeerbower/llama-3-Stheno-Mahou-8B"
      ]
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/mhMDEV-VH2cbHvThdZA0T.png",
    "summary": "My GGUF-IQ-Imatrix quants for **nbeerbower/llama-3-Stheno-Mahou-8B**. \"A potential precious hidden gem, will you polish this rough diamond?\" This is a merge of two very interesting models, aimed at roleplaying usage. !image/png > [!TIP] > **Personal-support:**  > I apologize for disrupting your experience.  > Currently I'm working on moving for a better internet provider.  > If you **want** and you are **able to**...  > You can **spare some change over here (Ko-fi)**.  > > **Author-support:**  > You can support the author **at their own page**. > [!IMPORTANT] > **Quantization process:**  > For future reference, these quants have been done after the fixes from **#6920** have been merged.  > Imatrix data was generated from the FP16-GGUF and the final conversions used BF16-GGUF for the quantization process.  > This was a bit more disk and compute intensive but hopefully avoided any losses during conversion.  > If you noticed any issues let me know in the discussions. > [!NOTE] > **General usage:**  > Use the latest version of **KoboldCpp**.  > Remember that you can also use --flashattention on KoboldCpp now even with non-RTX cards for reduced VRAM usage.  > For **8GB VRAM** GPUs, I recommend the **Q4_K_M-imat** quant for up to 12288 context sizes.  > For **12GB VRAM** GPUs, the **Q5_K_M-imat** quant will give you a great size/quality balance.  > > **Resources:**  > You can find out more about how each quant stacks up against each other and their types **here** and **here**, respectively. > > **Presets:**  > Some compatible SillyTavern presets can be found **here (Virt's Roleplay Presets)**, experiment with Llama-3 and ChatML.   Check **discussions such as this one** for other recommendations and samplers. -->",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\ninference: false\ntags:\n- roleplay\n- llama3\n- sillytavern\nbase_model:\n- nbeerbower/llama-3-Stheno-Mahou-8B\n---\n\n# #roleplay #sillytavern #llama3\n\nMy GGUF-IQ-Imatrix quants for [**nbeerbower/llama-3-Stheno-Mahou-8B**](https://huggingface.co/nbeerbower/llama-3-Stheno-Mahou-8B).\n\n\"A potential precious hidden gem, will you polish this rough diamond?\"\n\nThis is a merge of two very interesting models, aimed at roleplaying usage.\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/mhMDEV-VH2cbHvThdZA0T.png)\n\n> [!TIP]\n> **Personal-support:** <br>\n> I apologize for disrupting your experience. <br>\n> Currently I'm working on moving for a better internet provider. <br>\n> If you **want** and you are **able to**... <br>\n> You can [**spare some change over here (Ko-fi)**](https://ko-fi.com/Lewdiculous). <br>\n>\n> **Author-support:** <br>\n> You can support the author [**at their own page**](https://huggingface.co/nbeerbower).\n\n> [!IMPORTANT]\n> **Quantization process:** <br>\n> For future reference, these quants have been done after the fixes from [**#6920**](https://github.com/ggerganov/llama.cpp/pull/6920) have been merged. <br>\n> Imatrix data was generated from the FP16-GGUF and the final conversions used BF16-GGUF for the quantization process. <br>\n> This was a bit more disk and compute intensive but hopefully avoided any losses during conversion. <br>\n> If you noticed any issues let me know in the discussions.\n\n> [!NOTE]\n> **General usage:** <br>\n> Use the latest version of **KoboldCpp**. <br>\n> Remember that you can also use `--flashattention` on KoboldCpp now even with non-RTX cards for reduced VRAM usage. <br>\n> For **8GB VRAM** GPUs, I recommend the **Q4_K_M-imat** quant for up to 12288 context sizes. <br>\n> For **12GB VRAM** GPUs, the **Q5_K_M-imat** quant will give you a great size/quality balance. <br>\n>\n> **Resources:** <br>\n> You can find out more about how each quant stacks up against each other and their types [**here**](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) and [**here**](https://rentry.org/llama-cpp-quants-or-fine-ill-do-it-myself-then-pt-2), respectively.\n> \n> **Presets:** <br>\n> Some compatible SillyTavern presets can be found [**here (Virt's Roleplay Presets)**](https://huggingface.co/Virt-io/SillyTavern-Presets), experiment with Llama-3 and ChatML. <br>\n<!-- > Check [**discussions such as this one**](https://huggingface.co/Virt-io/SillyTavern-Presets/discussions/5#664d6fb87c563d4d95151baa) for other recommendations and samplers.\n-->\n\n## **Original model text information:**\n\n# llama-3-Stheno-Mahou-8B\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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [flammenai/Mahou-1.2-llama3-8B](https://huggingface.co/flammenai/Mahou-1.2-llama3-8B) as a base.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [flammenai/Mahou-1.1-llama3-8B](https://huggingface.co/flammenai/Mahou-1.1-llama3-8B)\n* [Sao10K/L3-8B-Stheno-v3.1](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.1)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nmodels:\n  - model: flammenai/Mahou-1.1-llama3-8B\n  - model: Sao10K/L3-8B-Stheno-v3.1\nmerge_method: model_stock\nbase_model: flammenai/Mahou-1.2-llama3-8B\ndtype: bfloat16\n\n\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "roleplay",
    "llama3",
    "sillytavern",
    "en",
    "arxiv:2403.19522",
    "base_model:nbeerbower/llama-3-Stheno-Mahou-8B",
    "base_model:quantized:nbeerbower/llama-3-Stheno-Mahou-8B",
    "license:apache-2.0",
    "region:us",
    "imatrix"
  ],
  "likes": 22,
  "downloads": 218,
  "gated": false,
  "private": false,
  "last_modified": "2024-12-12T19:09:07.000Z",
  "created_at": "2024-05-29T19:27:40.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "665781ac5e2a89484876fb99",
  "id": "Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix",
  "modelId": "Lewdiculous/llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix",
  "sha": "fd9f34e0fcb2d42c6876b9b85efae032fcebedff",
  "createdAt": "2024-05-29T19:27:40.000Z",
  "lastModified": "2024-12-12T19:09:07.000Z",
  "author": "Lewdiculous",
  "downloads": 218,
  "likes": 22,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 14
}