richarderkhov/neversleep_-_llama-3-lumimaid-70b-v0.1-oas-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/d3QMaxy3peFTpSlWdWF-k.png",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models Llama-3-Lumimaid-70B-v0.1-OAS - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Llama-3-Lumimaid-70B-v0.1-OAS.Q2_K.gguf | Q2_K | 24.56GB | | Llama-3-Lumimaid-70B-v0.1-OAS.IQ3_XS.gguf | IQ3_XS | 27.29GB | | Llama-3-Lumimaid-70B-v0.1-OAS.IQ3_S.gguf | IQ3_S | 28.79GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K_S.gguf | Q3_K_S | 28.79GB | | Llama-3-Lumimaid-70B-v0.1-OAS.IQ3_M.gguf | IQ3_M | 29.74GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K.gguf | Q3_K | 31.91GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K_M.gguf | Q3_K_M | 31.91GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K_L.gguf | Q3_K_L | 34.59GB | | Llama-3-Lumimaid-70B-v0.1-OAS.IQ4_XS.gguf | IQ4_XS | 35.64GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q4_0.gguf | Q4_0 | 37.22GB | | Llama-3-Lumimaid-70B-v0.1-OAS.IQ4_NL.gguf | IQ4_NL | 37.58GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q4_K_S.gguf | Q4_K_S | 37.58GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q4_K.gguf | Q4_K | 39.6GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q4_K_M.gguf | Q4_K_M | 39.6GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q4_1.gguf | Q4_1 | 41.27GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q5_0.gguf | Q5_0 | 45.32GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q5_K_S.gguf | Q5_K_S | 45.32GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q5_K.gguf | Q5_K | 46.52GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q5_K_M.gguf | Q5_K_M | 46.52GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q5_1.gguf | Q5_1 | 49.36GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q6_K.gguf | Q6_K | 53.91GB | | Llama-3-Lumimaid-70B-v0.1-OAS.Q8_0.gguf | Q8_0 | 69.83GB | Original model description: --- license: cc-by-nc-4.0 tags: ---",
    "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\nLlama-3-Lumimaid-70B-v0.1-OAS - GGUF\n- Model creator: https://huggingface.co/NeverSleep/\n- Original model: https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1-OAS/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q2_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.Q2_K.gguf) | Q2_K | 24.56GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.IQ3_XS.gguf) | IQ3_XS | 27.29GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.IQ3_S.gguf) | IQ3_S | 28.79GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K_S.gguf) | Q3_K_S | 28.79GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.IQ3_M.gguf) | IQ3_M | 29.74GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K.gguf) | Q3_K | 31.91GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K_M.gguf) | Q3_K_M | 31.91GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.Q3_K_L.gguf) | Q3_K_L | 34.59GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.IQ4_XS.gguf) | IQ4_XS | 35.64GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q4_0.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/blob/main/Llama-3-Lumimaid-70B-v0.1-OAS.Q4_0.gguf) | Q4_0 | 37.22GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | IQ4_NL | 37.58GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q4_K_S | 37.58GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q4_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q4_K | 39.6GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q4_K_M | 39.6GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q4_1.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q4_1 | 41.27GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q5_0.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q5_0 | 45.32GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q5_K_S | 45.32GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q5_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q5_K | 46.52GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q5_K_M | 46.52GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q5_1.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q5_1 | 49.36GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q6_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q6_K | 53.91GB |\n| [Llama-3-Lumimaid-70B-v0.1-OAS.Q8_0.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf/tree/main/) | Q8_0 | 69.83GB |\n\n\n\n\nOriginal model description:\n---\nlicense: cc-by-nc-4.0\ntags:\n- not-for-all-audiences\n- nsfw\n---\n\n## Lumimaid 0.1\n\n<center><div style=\"width: 100%;\">\n    <img src=\"https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/d3QMaxy3peFTpSlWdWF-k.png\" style=\"display: block; margin: auto;\">\n</div></center>\n\nThis model uses the Llama3 **prompting format**\n\nLlama3 trained on our RP datasets, we tried to have a balance between the ERP and the RP, not too horny, but just enough.\n\nWe also added some non-RP dataset, making the model less dumb overall. It should look like a 40%/60% ratio for Non-RP/RP+ERP data.\n\nThis model includes the new Luminae dataset from Ikari.\n\nThis model have received the Orthogonal Activation Steering treatment, meaning it will rarely refuse any request.\n\nIf you consider trying this model please give us some feedback either on the Community tab on hf or on our [Discord Server](https://discord.gg/MtCVRWTZXY).\n\n## Credits:\n- Undi\n- IkariDev\n\n## Description\n\nThis repo contains FP16 files of Lumimaid-70B-v0.1-OAS.\n\nSwitch: [8B](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1) - [70B](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1) - [70B-alt](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1-alt) - [8B-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) - [70B-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1-OAS)\n\n## Training data used:\n- [Aesir datasets](https://huggingface.co/MinervaAI)\n- [NoRobots](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt)\n- [limarp](https://huggingface.co/datasets/lemonilia/LimaRP) - 8k ctx\n- [toxic-dpo-v0.1-sharegpt](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt)\n- [ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal)\n- Luminae-i1 (70B/70B-alt) (i2 was not existing when the 70b started training) | Luminae-i2 (8B) (this one gave better results on the 8b) - Ikari's Dataset\n- [Squish42/bluemoon-fandom-1-1-rp-cleaned](https://huggingface.co/datasets/Squish42/bluemoon-fandom-1-1-rp-cleaned) - 50% (randomly)\n- [NobodyExistsOnTheInternet/PIPPAsharegptv2test](https://huggingface.co/datasets/NobodyExistsOnTheInternet/PIPPAsharegptv2test) - 5% (randomly)\n- [cgato/SlimOrcaDedupCleaned](https://huggingface.co/datasets/cgato/SlimOrcaDedupCleaned) - 5% (randomly)\n- Airoboros (reduced)\n- [Capybara](https://huggingface.co/datasets/Undi95/Capybara-ShareGPT/) (reduced)\n\n\n## Models used (only for 8B)\n\n- Initial LumiMaid 8B Finetune\n- Undi95/Llama-3-Unholy-8B-e4\n- Undi95/Llama-3-LewdPlay-8B\n\n## Prompt template: Llama3\n\n```\n<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n{output}<|eot_id|>\n```\n\n## Others\n\nUndi: If you want to support us, you can [here](https://ko-fi.com/undiai).\n\nIkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 139,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-30T06:19:14.000Z",
  "created_at": "2024-10-29T12:45:09.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6720d8d5f881c98484268777",
  "id": "RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf",
  "modelId": "RichardErkhov/NeverSleep_-_Llama-3-Lumimaid-70B-v0.1-OAS-gguf",
  "sha": "aa6519e555b47ab39d5467816086e05caa7b765e",
  "createdAt": "2024-10-29T12:45:09.000Z",
  "lastModified": "2024-10-30T06:19:14.000Z",
  "author": "RichardErkhov",
  "downloads": 139,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 36
}