richarderkhov/grimjim_-_kitsunebi-v1-gemma2-8k-9b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This repo contains a merge of pre-trained Gemma 2 9B Instruct language models created using mergekit. None of the components of this merge were trained for roleplay nor intended for it. Despite this, the resulting model can be used effectively for that function. The virtue of this model lies in its coherence, as opposed to textual richness. This project utilizes HODACHI/EZO-Common-9B-gemma-2-it, a model based on gemma-2 and fine-tuned by Axcxept co., ltd. Its primary goal was to perform well in Japanese language tasks. Model training leveraged context-based synthesized instruction pre-training data for supervised multitask pre-training (abstract). We also used princeton-nlp/gemma-2-9b-it-SimPO, a demonstration of Simple Preference Optimization (abstract).",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nKitsunebi-v1-Gemma2-8k-9B - GGUF\n- Model creator: https://huggingface.co/grimjim/\n- Original model: https://huggingface.co/grimjim/Kitsunebi-v1-Gemma2-8k-9B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q2_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q2_K.gguf) | Q2_K | 3.54GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.IQ3_XS.gguf) | IQ3_XS | 3.86GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.IQ3_S.gguf) | IQ3_S | 4.04GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q3_K_S.gguf) | Q3_K_S | 4.04GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.IQ3_M.gguf) | IQ3_M | 4.19GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q3_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q3_K.gguf) | Q3_K | 4.43GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q3_K_M.gguf) | Q3_K_M | 4.43GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q3_K_L.gguf) | Q3_K_L | 4.78GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.IQ4_XS.gguf) | IQ4_XS | 4.86GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q4_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q4_0.gguf) | Q4_0 | 5.07GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.IQ4_NL.gguf) | IQ4_NL | 5.1GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q4_K_S.gguf) | Q4_K_S | 5.1GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q4_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q4_K.gguf) | Q4_K | 5.37GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q4_K_M.gguf) | Q4_K_M | 5.37GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q4_1.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q4_1.gguf) | Q4_1 | 5.55GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q5_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q5_0.gguf) | Q5_0 | 6.04GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q5_K_S.gguf) | Q5_K_S | 6.04GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q5_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q5_K.gguf) | Q5_K | 6.19GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q5_K_M.gguf) | Q5_K_M | 6.19GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q5_1.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q5_1.gguf) | Q5_1 | 6.52GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q6_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q6_K.gguf) | Q6_K | 7.07GB |\n| [Kitsunebi-v1-Gemma2-8k-9B.Q8_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf/blob/main/Kitsunebi-v1-Gemma2-8k-9B.Q8_0.gguf) | Q8_0 | 9.15GB |\n\n\n\n\nOriginal model description:\n---\nbase_model:\n- princeton-nlp/gemma-2-9b-it-SimPO\n- HODACHI/EZO-Common-9B-gemma-2-it\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\nlicense: gemma\npipeline_tag: text-generation\n---\n# Kitsunebi-v1-Gemma2-8k-9B\n\nThis repo contains a merge of pre-trained Gemma 2 9B Instruct language models created using [mergekit](https://github.com/cg123/mergekit).\n\nNone of the components of this merge were trained for roleplay nor intended for it. Despite this, the resulting model can be used effectively for that function. The virtue of this model lies in its coherence, as opposed to textual richness.\n\nThis project utilizes HODACHI/EZO-Common-9B-gemma-2-it, a model based on gemma-2 and fine-tuned by Axcxept co., ltd. Its primary goal was to perform well in Japanese language tasks. Model training leveraged context-based synthesized instruction pre-training data for supervised multitask pre-training [(abstract)](https://arxiv.org/abs/2406.14491).\n\nWe also used princeton-nlp/gemma-2-9b-it-SimPO, a demonstration of Simple Preference Optimization [(abstract)](https://arxiv.org/abs/2405.14734).\n\n## Merge Details\n### Merge Method\n\nThis model was merged using the SLERP merge method.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO)\n* [HODACHI/EZO-Common-9B-gemma-2-it](https://huggingface.co/HODACHI/EZO-Common-9B-gemma-2-it)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nslices:\n- sources:\n  - model: princeton-nlp/gemma-2-9b-it-SimPO\n    layer_range: [0, 42]\n  - model: HODACHI/EZO-Common-9B-gemma-2-it\n    layer_range: [0, 42]\nmerge_method: slerp\nbase_model: HODACHI/EZO-Common-9B-gemma-2-it\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```\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2406.14491",
    "arxiv:2405.14734",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 858,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-11T13:48:53.000Z",
  "created_at": "2024-09-11T10:19:39.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66e16ebbf61997681fd62447",
  "id": "RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf",
  "modelId": "RichardErkhov/grimjim_-_Kitsunebi-v1-Gemma2-8k-9B-gguf",
  "sha": "8b6eff6e0d0c67386f4ff7a616aef1bf37844547",
  "createdAt": "2024-09-11T10:19:39.000Z",
  "lastModified": "2024-09-11T13:48:53.000Z",
  "author": "RichardErkhov",
  "downloads": 858,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}