richarderkhov/sao10k_-_l3-8b-lunaris-v1-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models L3-8B-Lunaris-v1 - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | L3-8B-Lunaris-v1.Q2_K.gguf | Q2_K | 2.96GB | | L3-8B-Lunaris-v1.IQ3_XS.gguf | IQ3_XS | 3.28GB | | L3-8B-Lunaris-v1.IQ3_S.gguf | IQ3_S | 3.43GB | | L3-8B-Lunaris-v1.Q3_K_S.gguf | Q3_K_S | 3.41GB | | L3-8B-Lunaris-v1.IQ3_M.gguf | IQ3_M | 3.52GB | | L3-8B-Lunaris-v1.Q3_K.gguf | Q3_K | 3.74GB | | L3-8B-Lunaris-v1.Q3_K_M.gguf | Q3_K_M | 3.74GB | | L3-8B-Lunaris-v1.Q3_K_L.gguf | Q3_K_L | 4.03GB | | L3-8B-Lunaris-v1.IQ4_XS.gguf | IQ4_XS | 4.18GB | | L3-8B-Lunaris-v1.Q4_0.gguf | Q4_0 | 4.34GB | | L3-8B-Lunaris-v1.IQ4_NL.gguf | IQ4_NL | 4.38GB | | L3-8B-Lunaris-v1.Q4_K_S.gguf | Q4_K_S | 4.37GB | | L3-8B-Lunaris-v1.Q4_K.gguf | Q4_K | 4.58GB | | L3-8B-Lunaris-v1.Q4_K_M.gguf | Q4_K_M | 4.58GB | | L3-8B-Lunaris-v1.Q4_1.gguf | Q4_1 | 4.78GB | | L3-8B-Lunaris-v1.Q5_0.gguf | Q5_0 | 5.21GB | | L3-8B-Lunaris-v1.Q5_K_S.gguf | Q5_K_S | 5.21GB | | L3-8B-Lunaris-v1.Q5_K.gguf | Q5_K | 5.34GB | | L3-8B-Lunaris-v1.Q5_K_M.gguf | Q5_K_M | 5.34GB | | L3-8B-Lunaris-v1.Q5_1.gguf | Q5_1 | 5.65GB | | L3-8B-Lunaris-v1.Q6_K.gguf | Q6_K | 6.14GB | | L3-8B-Lunaris-v1.Q8_0.gguf | Q8_0 | 7.95GB | Original model description: --- license: llama3 language: --- A generalist / roleplaying model merge based on Llama 3. Models are selected from my personal experience while using them. I personally think this is an improvement over Stheno v3.2, considering the other models helped balance out its creativity and at the same time improving its logic. Settings: `` Instruct // Context Template: Llama-3-Instruct Temperature: 1.4 min_p: 0.1 ` --- Merging seems to be a black box magic though? In my personal experience merging multiple models from different datasets / data works better than combining them all in one. *Values chosen are from long-running personal experimentation since Llama-2 Merging Era. I have tweaked them to fit this recipe.* Mergekit Config ` models: parameters: density: 0.4 weight: 0.25 parameters: density: 0.5 weight: 0.3 parameters: density: 0.6 weight: 0.35 parameters: density: 0.7 weight: 0.4 merge_method: ties base_model: meta-llama/Meta-Llama-3-8B-Instruct parameters: int8_mask: true rescale: true normalize: false 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\nL3-8B-Lunaris-v1 - GGUF\n- Model creator: https://huggingface.co/Sao10K/\n- Original model: https://huggingface.co/Sao10K/L3-8B-Lunaris-v1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [L3-8B-Lunaris-v1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q2_K.gguf) | Q2_K | 2.96GB |\n| [L3-8B-Lunaris-v1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [L3-8B-Lunaris-v1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [L3-8B-Lunaris-v1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [L3-8B-Lunaris-v1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [L3-8B-Lunaris-v1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q3_K.gguf) | Q3_K | 3.74GB |\n| [L3-8B-Lunaris-v1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [L3-8B-Lunaris-v1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [L3-8B-Lunaris-v1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [L3-8B-Lunaris-v1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [L3-8B-Lunaris-v1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [L3-8B-Lunaris-v1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [L3-8B-Lunaris-v1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q4_K.gguf) | Q4_K | 4.58GB |\n| [L3-8B-Lunaris-v1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [L3-8B-Lunaris-v1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [L3-8B-Lunaris-v1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [L3-8B-Lunaris-v1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [L3-8B-Lunaris-v1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q5_K.gguf) | Q5_K | 5.34GB |\n| [L3-8B-Lunaris-v1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [L3-8B-Lunaris-v1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [L3-8B-Lunaris-v1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q6_K.gguf) | Q6_K | 6.14GB |\n| [L3-8B-Lunaris-v1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf/blob/main/L3-8B-Lunaris-v1.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlicense: llama3\nlanguage:\n- en\n---\n\nA generalist / roleplaying model merge based on Llama 3. Models are selected from my personal experience while using them.\n\nI personally think this is an improvement over Stheno v3.2, considering the other models helped balance out its creativity and at the same time improving its logic.\n\nSettings:\n```\nInstruct // Context Template: Llama-3-Instruct\nTemperature: 1.4\nmin_p: 0.1\n```\n\n---\n\nMerging seems to be a black box magic though? In my personal experience merging multiple models from different datasets / data works better than combining them all in one.\n\n*Values chosen are from long-running personal experimentation since Llama-2 Merging Era. I have tweaked them to fit this recipe.*\n\nMergekit Config \n```\nmodels:\n  - model: meta-llama/Meta-Llama-3-8B-Instruct\n  - model: crestf411/L3-8B-sunfall-v0.1 # Another RP Model trained on... stuff\n    parameters:\n      density: 0.4\n      weight: 0.25\n  - model: Hastagaras/Jamet-8B-L3-MK1 - # Another RP / Storytelling Model\n    parameters:\n      density: 0.5\n      weight: 0.3\n  - model: maldv/badger-iota-llama-3-8b #Megamerge - Helps with General Knowledge\n    parameters:\n      density: 0.6\n      weight: 0.35\n  - model: Sao10K/Stheno-3.2-Beta # This is Stheno v3.2's Initial Name\n    parameters:\n      density: 0.7\n      weight: 0.4\nmerge_method: ties\nbase_model: meta-llama/Meta-Llama-3-8B-Instruct\nparameters:\n  int8_mask: true\n  rescale: true\n  normalize: false\ndtype: bfloat16\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 91,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-22T09:28:47.000Z",
  "created_at": "2024-08-22T07:31:50.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66c6e966698ebf998aebeddd",
  "id": "RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf",
  "modelId": "RichardErkhov/Sao10K_-_L3-8B-Lunaris-v1-gguf",
  "sha": "eaca0e999e1ea8107e7b5e83457eff8a367de1ab",
  "createdAt": "2024-08-22T07:31:50.000Z",
  "lastModified": "2024-08-22T09:28:47.000Z",
  "author": "RichardErkhov",
  "downloads": 91,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}