richarderkhov/tannedbum_-_l3-nymeria-maid-8b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://huggingface.co/tannedbum/L3-Nymeria-Maid-8B-exl2/resolve/main/Nymeria.png?",
    "summary": "This is a merge of pre-trained language models created using mergekit. This model was merged using the slerp merge method. ### Models Merged The following models were included in the merge: * Sao10K/L3-8B-Stheno-v3.2 * princeton-nlp/Llama-3-Instruct-8B-SimPO ### 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: Sao10K/L3-8B-Stheno-v3.2 parameters: t: value: [0.2, 0.4, 0.4, 0.6] value: [0.8, 0.6, 0.6, 0.4] dtype: bfloat16 `` ---",
    "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\nL3-Nymeria-Maid-8B - GGUF\n- Model creator: https://huggingface.co/tannedbum/\n- Original model: https://huggingface.co/tannedbum/L3-Nymeria-Maid-8B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [L3-Nymeria-Maid-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q2_K.gguf) | Q2_K | 2.96GB |\n| [L3-Nymeria-Maid-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [L3-Nymeria-Maid-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [L3-Nymeria-Maid-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [L3-Nymeria-Maid-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [L3-Nymeria-Maid-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q3_K.gguf) | Q3_K | 3.74GB |\n| [L3-Nymeria-Maid-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [L3-Nymeria-Maid-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [L3-Nymeria-Maid-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [L3-Nymeria-Maid-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [L3-Nymeria-Maid-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [L3-Nymeria-Maid-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [L3-Nymeria-Maid-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q4_K.gguf) | Q4_K | 4.58GB |\n| [L3-Nymeria-Maid-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [L3-Nymeria-Maid-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [L3-Nymeria-Maid-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [L3-Nymeria-Maid-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [L3-Nymeria-Maid-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q5_K.gguf) | Q5_K | 5.34GB |\n| [L3-Nymeria-Maid-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [L3-Nymeria-Maid-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [L3-Nymeria-Maid-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q6_K.gguf) | Q6_K | 6.14GB |\n| [L3-Nymeria-Maid-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf/blob/main/L3-Nymeria-Maid-8B.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nbase_model:\n- princeton-nlp/Llama-3-Instruct-8B-SimPO\n- Sao10K/L3-8B-Stheno-v3.2\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\n- roleplay\n- sillytavern\n- llama3\n- not-for-all-audiences\nlicense: cc-by-nc-4.0\nlanguage:\n- en\n---\n![Nymeria](https://huggingface.co/tannedbum/L3-Nymeria-Maid-8B-exl2/resolve/main/Nymeria.png?)\n\n## This version is solely for scientific purposes, of course.\n\nNymeria is the balanced version, doesn't force nsfw. Nymeria-Maid has more Stheno's weights, leans more on nsfw and is more submissive.\n\n\n## SillyTavern\n\n## Text Completion presets\n```\ntemp 0.9\ntop_k 30\ntop_p 0.75\nmin_p 0.2\nrep_pen 1.1\nsmooth_factor 0.25\nsmooth_curve 1\n```\n## Advanced Formatting\n\n[Context & Instruct preset by Virt-io](https://huggingface.co/Virt-io/SillyTavern-Presets/tree/main/Prompts/LLAMA-3/v1.9)\n\n Instruct Mode: Enabled\n\n\n\n# merge\n\nThis is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).\n\nThis model was merged using the slerp merge method.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2)\n* [princeton-nlp/Llama-3-Instruct-8B-SimPO](https://huggingface.co/princeton-nlp/Llama-3-Instruct-8B-SimPO)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\n\nslices:\n  - sources:\n      - model: Sao10K/L3-8B-Stheno-v3.2\n        layer_range: [0, 32]\n      - model: princeton-nlp/Llama-3-Instruct-8B-SimPO\n        layer_range: [0, 32]\nmerge_method: slerp\nbase_model: Sao10K/L3-8B-Stheno-v3.2\nparameters:\n  t:\n    - filter: self_attn\n      value: [0.2, 0.4, 0.4, 0.6]\n    - filter: mlp\n      value: [0.8, 0.6, 0.6, 0.4]\n    - value: 0.4\ndtype: bfloat16\n\n\n```\n\n---\n\n## Original model information:\n\n## Model: Sao10K/L3-8B-Stheno-v3.2\n\nStheno-v3.2-Zeta\n\n\nChanges compared to v3.1\n<br>\\- Included a mix of SFW and NSFW Storywriting Data, thanks to [Gryphe](https://huggingface.co/datasets/Gryphe/Opus-WritingPrompts)\n<br>\\- Included More Instruct / Assistant-Style Data\n<br>\\- Further cleaned up Roleplaying Samples from c2 Logs -> A few terrible, really bad samples escaped heavy filtering. Manual pass fixed it.\n<br>\\- Hyperparameter tinkering for training, resulting in lower loss levels.\n\n\nTesting Notes - Compared to v3.1\n<br>\\- Handles SFW / NSFW seperately better. Not as overly excessive with NSFW now. Kinda balanced.\n<br>\\- Better at Storywriting / Narration.\n<br>\\- Better at Assistant-type Tasks.\n<br>\\- Better Multi-Turn Coherency -> Reduced Issues?\n<br>\\- Slightly less creative? A worthy tradeoff. Still creative.\n<br>\\- Better prompt / instruction adherence.\n\n---\n\nWant to support my work ? My Ko-fi page: https://ko-fi.com/tannedbum\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 86,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-23T22:54:33.000Z",
  "created_at": "2024-08-23T19:26:36.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66c8e26cbaaf0e1ad9711eb4",
  "id": "RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf",
  "modelId": "RichardErkhov/tannedbum_-_L3-Nymeria-Maid-8B-gguf",
  "sha": "5d0dc3a8118807bb79444fc069a8f40d31ecd22d",
  "createdAt": "2024-08-23T19:26:36.000Z",
  "lastModified": "2024-08-23T22:54:33.000Z",
  "author": "RichardErkhov",
  "downloads": 86,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}