richarderkhov/neversleep_-_lumimaid-v0.2-8b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/TUcHg7LKNjfo0sni88Ps7.png",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models Lumimaid-v0.2-8B - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Lumimaid-v0.2-8B.Q2_K.gguf | Q2_K | 2.96GB | | Lumimaid-v0.2-8B.IQ3_XS.gguf | IQ3_XS | 3.28GB | | Lumimaid-v0.2-8B.IQ3_S.gguf | IQ3_S | 3.43GB | | Lumimaid-v0.2-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB | | Lumimaid-v0.2-8B.IQ3_M.gguf | IQ3_M | 3.52GB | | Lumimaid-v0.2-8B.Q3_K.gguf | Q3_K | 3.74GB | | Lumimaid-v0.2-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB | | Lumimaid-v0.2-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB | | Lumimaid-v0.2-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB | | Lumimaid-v0.2-8B.Q4_0.gguf | Q4_0 | 4.34GB | | Lumimaid-v0.2-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB | | Lumimaid-v0.2-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB | | Lumimaid-v0.2-8B.Q4_K.gguf | Q4_K | 4.58GB | | Lumimaid-v0.2-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB | | Lumimaid-v0.2-8B.Q4_1.gguf | Q4_1 | 4.78GB | | Lumimaid-v0.2-8B.Q5_0.gguf | Q5_0 | 5.21GB | | Lumimaid-v0.2-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB | | Lumimaid-v0.2-8B.Q5_K.gguf | Q5_K | 5.34GB | | Lumimaid-v0.2-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB | | Lumimaid-v0.2-8B.Q5_1.gguf | Q5_1 | 5.65GB | | Lumimaid-v0.2-8B.Q6_K.gguf | Q6_K | 6.14GB | | Lumimaid-v0.2-8B.Q8_0.gguf | Q8_0 | 3.77GB | 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\nLumimaid-v0.2-8B - GGUF\n- Model creator: https://huggingface.co/NeverSleep/\n- Original model: https://huggingface.co/NeverSleep/Lumimaid-v0.2-8B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Lumimaid-v0.2-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q2_K.gguf) | Q2_K | 2.96GB |\n| [Lumimaid-v0.2-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [Lumimaid-v0.2-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [Lumimaid-v0.2-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [Lumimaid-v0.2-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [Lumimaid-v0.2-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q3_K.gguf) | Q3_K | 3.74GB |\n| [Lumimaid-v0.2-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [Lumimaid-v0.2-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [Lumimaid-v0.2-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [Lumimaid-v0.2-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [Lumimaid-v0.2-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [Lumimaid-v0.2-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [Lumimaid-v0.2-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q4_K.gguf) | Q4_K | 4.58GB |\n| [Lumimaid-v0.2-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [Lumimaid-v0.2-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [Lumimaid-v0.2-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [Lumimaid-v0.2-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [Lumimaid-v0.2-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q5_K.gguf) | Q5_K | 5.34GB |\n| [Lumimaid-v0.2-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [Lumimaid-v0.2-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [Lumimaid-v0.2-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q6_K.gguf) | Q6_K | 6.14GB |\n| [Lumimaid-v0.2-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf/blob/main/Lumimaid-v0.2-8B.Q8_0.gguf) | Q8_0 | 3.77GB |\n\n\n\n\nOriginal model description:\n---\nlicense: cc-by-nc-4.0\ntags:\n- not-for-all-audiences\n- nsfw\n---\n## Lumimaid 0.2\n<img src=\"https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/TUcHg7LKNjfo0sni88Ps7.png\" alt=\"Image\" style=\"display: block; margin-left: auto; margin-right: auto; width: 65%;\">\n<div style=\"text-align: center; font-size: 30px;\">\n    <a href=\"https://huggingface.co/NeverSleep/Lumimaid-v0.2-8B\">[8b]</a> -\n    <a href=\"https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B\">12b</a> -\n    <a href=\"https://huggingface.co/NeverSleep/Lumimaid-v0.2-70B\">70b</a> -\n    <a href=\"https://huggingface.co/NeverSleep/Lumimaid-v0.2-123B\">123b</a>\n</div>\n\n### This model is based on: [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)\nWandb: https://wandb.ai/undis95/Lumi-Llama-3-1-8B?nw=nwuserundis95\n\nLumimaid 0.1 -> 0.2 is a HUGE step up dataset wise.\n\nAs some people have told us our models are sloppy, Ikari decided to say fuck it and literally nuke all chats out with most slop.\n\nOur dataset stayed the same since day one, we added data over time, cleaned them, and repeat. After not releasing model for a while because we were never satisfied, we think it's time to come back!\n\n\n## Prompt template: Llama-3-Instruct\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## Credits:\n- Undi\n- IkariDev\n\n## Training data we used to make our dataset:\n\n- [Epiculous/Gnosis](https://huggingface.co/Epiculous/Gnosis)\n- [ChaoticNeutrals/Luminous_Opus](https://huggingface.co/datasets/ChaoticNeutrals/Luminous_Opus)\n- [ChaoticNeutrals/Synthetic-Dark-RP](https://huggingface.co/datasets/ChaoticNeutrals/Synthetic-Dark-RP)\n- [ChaoticNeutrals/Synthetic-RP](https://huggingface.co/datasets/ChaoticNeutrals/Synthetic-RP)\n- [Gryphe/Sonnet3.5-SlimOrcaDedupCleaned](https://huggingface.co/datasets/Gryphe/Sonnet3.5-SlimOrcaDedupCleaned)\n- [Gryphe/Opus-WritingPrompts](https://huggingface.co/datasets/Gryphe/Opus-WritingPrompts)\n- [meseca/writing-opus-6k](https://huggingface.co/datasets/meseca/writing-opus-6k)\n- [meseca/opus-instruct-9k](https://huggingface.co/datasets/meseca/opus-instruct-9k)\n- [PJMixers/grimulkan_theory-of-mind-ShareGPT](https://huggingface.co/datasets/PJMixers/grimulkan_theory-of-mind-ShareGPT)\n- [NobodyExistsOnTheInternet/ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal)\n- [Undi95/toxic-dpo-v0.1-sharegpt](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt)\n- [cgato/SlimOrcaDedupCleaned](https://huggingface.co/datasets/cgato/SlimOrcaDedupCleaned)\n- [kalomaze/Opus_Instruct_25k](https://huggingface.co/datasets/kalomaze/Opus_Instruct_25k)\n- [Doctor-Shotgun/no-robots-sharegpt](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt)\n- [Norquinal/claude_multiround_chat_30k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_30k)\n- [nothingiisreal/Claude-3-Opus-Instruct-15K](https://huggingface.co/datasets/nothingiisreal/Claude-3-Opus-Instruct-15K)\n- All the Aesirs dataset, cleaned, unslopped\n- All le luminae dataset, cleaned, unslopped\n- Small part of Airoboros reduced\n\nWe sadly didn't find the sources of the following, DM us if you recognize your set !\n\n- Opus_Instruct-v2-6.5K-Filtered-v2-sharegpt\n- claude_sharegpt_trimmed\n- CapybaraPure_Decontaminated-ShareGPT_reduced\n\n## Datasets credits:\n- Epiculous\n- ChaoticNeutrals\n- Gryphe\n- meseca\n- PJMixers\n- NobodyExistsOnTheInternet\n- cgato\n- kalomaze\n- Doctor-Shotgun\n- Norquinal\n- nothingiisreal\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": 99,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-05T01:51:32.000Z",
  "created_at": "2024-08-04T22:06:25.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66affb61d7f2b182865a2f4e",
  "id": "RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf",
  "modelId": "RichardErkhov/NeverSleep_-_Lumimaid-v0.2-8B-gguf",
  "sha": "3409e8dc227eafbbd7ec75f455d48035f457dee0",
  "createdAt": "2024-08-04T22:06:25.000Z",
  "lastModified": "2024-08-05T01:51:32.000Z",
  "author": "RichardErkhov",
  "downloads": 99,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}