richarderkhov/mergekit-community_-_l3.1-pneuma-8b-v1-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This is a merge of pre-trained language models created using mergekit.",
    "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\nL3.1-Pneuma-8B-v1 - GGUF\n- Model creator: https://huggingface.co/mergekit-community/\n- Original model: https://huggingface.co/mergekit-community/L3.1-Pneuma-8B-v1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [L3.1-Pneuma-8B-v1.Q2_K.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q2_K.gguf) | Q2_K | 2.96GB |\n| [L3.1-Pneuma-8B-v1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [L3.1-Pneuma-8B-v1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [L3.1-Pneuma-8B-v1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [L3.1-Pneuma-8B-v1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [L3.1-Pneuma-8B-v1.Q3_K.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q3_K.gguf) | Q3_K | 3.74GB |\n| [L3.1-Pneuma-8B-v1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [L3.1-Pneuma-8B-v1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [L3.1-Pneuma-8B-v1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [L3.1-Pneuma-8B-v1.Q4_0.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [L3.1-Pneuma-8B-v1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [L3.1-Pneuma-8B-v1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [L3.1-Pneuma-8B-v1.Q4_K.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q4_K.gguf) | Q4_K | 4.58GB |\n| [L3.1-Pneuma-8B-v1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [L3.1-Pneuma-8B-v1.Q4_1.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [L3.1-Pneuma-8B-v1.Q5_0.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [L3.1-Pneuma-8B-v1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [L3.1-Pneuma-8B-v1.Q5_K.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q5_K.gguf) | Q5_K | 5.34GB |\n| [L3.1-Pneuma-8B-v1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [L3.1-Pneuma-8B-v1.Q5_1.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [L3.1-Pneuma-8B-v1.Q6_K.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q6_K.gguf) | Q6_K | 6.14GB |\n| [L3.1-Pneuma-8B-v1.Q8_0.gguf](https://huggingface.co/RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf/blob/main/L3.1-Pneuma-8B-v1.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nbase_model:\n- Replete-AI/L3-Pneuma-8B\n- ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\n\n---\n# merge\n\nThis is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).\n\n## Merge Details\n### Merge Method\n\nThis model was merged using the della_linear merge method using [ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2](https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2) as a base.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [Replete-AI/L3-Pneuma-8B](https://huggingface.co/Replete-AI/L3-Pneuma-8B)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nout_dtype: bfloat16\ndtype: float32\ntokenizer_source: base\nmerge_method: della_linear\nparameters:\n  int8_mask: true\n  density: 0.5\n  epsilon: 0.04\n  lambda: 1.05\nbase_model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2\nmodels:\n  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2\n    parameters:\n      weight:\n        - filter: v_proj\n          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]\n        - filter: o_proj\n          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]\n        - filter: up_proj\n          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]\n        - filter: gate_proj\n          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]\n        - filter: down_proj\n          value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]\n        - value: 1\n  - model: Replete-AI/L3-Pneuma-8B\n    parameters:\n      weight:\n        - filter: v_proj\n          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]\n        - filter: o_proj\n          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]\n        - filter: up_proj\n          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]\n        - filter: gate_proj\n          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]\n        - filter: down_proj\n          value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]\n        - value: 0\n\n```\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 143,
  "gated": false,
  "private": false,
  "last_modified": "2025-05-16T08:51:47.000Z",
  "created_at": "2025-05-16T06:34:27.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6826dc73790c24d2815b90e7",
  "id": "RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf",
  "modelId": "RichardErkhov/mergekit-community_-_L3.1-Pneuma-8B-v1-gguf",
  "sha": "40823577fa20ede92e2b53c6e2bd369fef06b2bb",
  "createdAt": "2025-05-16T06:34:27.000Z",
  "lastModified": "2025-05-16T08:51:47.000Z",
  "author": "RichardErkhov",
  "downloads": 143,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}