richarderkhov/na0s_-_llama-3.1-8b-pruned-4-layers-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://i.ibb.co/61G1ZZG/DALL-E-2024-08-08-05-39-49-Create-a-visually-captivating-image-for-a-model-card-representing-a-prune.webp",
    "summary": "This is a merge of meta-llama/Meta-Llama-3.1-8B created using mergekit, with respect to the paper \"The Unreasonable Ineffectiveness of the Deeper Layers\"",
    "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-3.1-8B-Pruned-4-Layers - GGUF\n- Model creator: https://huggingface.co/Na0s/\n- Original model: https://huggingface.co/Na0s/Llama-3.1-8B-Pruned-4-Layers/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Llama-3.1-8B-Pruned-4-Layers.Q2_K.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q2_K.gguf) | Q2_K | 2.59GB |\n| [Llama-3.1-8B-Pruned-4-Layers.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.IQ3_XS.gguf) | IQ3_XS | 2.86GB |\n| [Llama-3.1-8B-Pruned-4-Layers.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.IQ3_S.gguf) | IQ3_S | 2.99GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q3_K_S.gguf) | Q3_K_S | 2.98GB |\n| [Llama-3.1-8B-Pruned-4-Layers.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.IQ3_M.gguf) | IQ3_M | 3.07GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q3_K.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q3_K.gguf) | Q3_K | 3.25GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q3_K_M.gguf) | Q3_K_M | 3.25GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q3_K_L.gguf) | Q3_K_L | 3.49GB |\n| [Llama-3.1-8B-Pruned-4-Layers.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.IQ4_XS.gguf) | IQ4_XS | 3.63GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q4_0.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q4_0.gguf) | Q4_0 | 1.7GB |\n| [Llama-3.1-8B-Pruned-4-Layers.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.IQ4_NL.gguf) | IQ4_NL | 3.8GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q4_K_S.gguf) | Q4_K_S | 3.79GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q4_K.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q4_K.gguf) | Q4_K | 3.97GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q4_K_M.gguf) | Q4_K_M | 3.97GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q4_1.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q4_1.gguf) | Q4_1 | 4.14GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q5_0.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q5_0.gguf) | Q5_0 | 4.52GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q5_K_S.gguf) | Q5_K_S | 4.52GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q5_K.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q5_K.gguf) | Q5_K | 4.62GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q5_K_M.gguf) | Q5_K_M | 4.62GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q5_1.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q5_1.gguf) | Q5_1 | 4.89GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q6_K.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q6_K.gguf) | Q6_K | 5.31GB |\n| [Llama-3.1-8B-Pruned-4-Layers.Q8_0.gguf](https://huggingface.co/RichardErkhov/Na0s_-_Llama-3.1-8B-Pruned-4-Layers-gguf/blob/main/Llama-3.1-8B-Pruned-4-Layers.Q8_0.gguf) | Q8_0 | 6.87GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\npipeline_tag: text-generation\n---\n\n<a href=\"https://ibb.co/k9z9yyz\"><img src=\"https://i.ibb.co/61G1ZZG/DALL-E-2024-08-08-05-39-49-Create-a-visually-captivating-image-for-a-model-card-representing-a-prune.webp\" alt=\"DALL-E-2024-08-08-05-39-49-Create-a-visually-captivating-image-for-a-model-card-representing-a-prune\" border=\"0\"></a><br /><a target='_blank' href='https://usefulwebtool.com/fr/convertir-minuscules-majuscules'></a><br />\n\n# Na0s/Llama-3.1-8b-Pruned-4-Layers\n\nThis is a merge of meta-llama/Meta-Llama-3.1-8B created using [mergekit](https://github.com/cg123/mergekit), with respect to the paper [\"The Unreasonable Ineffectiveness of the Deeper Layers\"](https://arxiv.org/pdf/2403.17887)\n\n\n## Merge Details\n### Merge Method\n\nThis model was merged using the passthrough merge method.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\ndtype: bfloat16\nmerge_method: passthrough\nslices:\n- sources:\n  - layer_range: [0, 23]\n    model: meta-llama/Meta-Llama-3.1-8B\n- sources:\n  - layer_range: [28, 32]\n    model: meta-llama/Meta-Llama-3.1-8B\n```\n\n## Evaluation\n\nMMLU Pro 0-shot: 0.2642\n\n\n#### Evaluation Data\n\n<!-- This should link to a Dataset Card if possible. -->\n\n[TIGER-AI-Lab/MMLU-Pro]\n\n\n## Environmental Impact\n\n<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->\n\nCarbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).\n\n<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2403.17887",
    "arxiv:1910.09700",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 3914,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-24T20:48:38.000Z",
  "created_at": "2024-08-04T17:33:16.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66afbb5c1ca0b39e0b8e5aa3",
  "id": "RichardErkhov/Na0s_-_Llama-3.1-8b-Pruned-4-Layers-gguf",
  "modelId": "RichardErkhov/Na0s_-_Llama-3.1-8b-Pruned-4-Layers-gguf",
  "sha": "f1d7fbae626542d2efac083bd74a6277a75431ad",
  "createdAt": "2024-08-04T17:33:16.000Z",
  "lastModified": "2024-08-24T20:48:38.000Z",
  "author": "RichardErkhov",
  "downloads": 3914,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 46
}