richarderkhov/grimjim_-_llama-3.1-8b-instruct-abliterated_via_adapter-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a merge of pre-trained language models created using mergekit. A LoRA was applied to \"abliterate\" refusals in meta-llama/Meta-Llama-3.1-8B-Instruct. The result appears to work despite the LoRA having been derived from Llama 3 instead of Llama 3.1, which implies that there is significant feature commonality between the 3 and 3.1 models. The LoRA was extracted from failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 using meta-llama/Meta-Llama-3-8B-Instruct as a base. Built with Llama.",
    "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-Instruct-abliterated_via_adapter - GGUF\n- Model creator: https://huggingface.co/grimjim/\n- Original model: https://huggingface.co/grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q2_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q2_K.gguf) | Q2_K | 2.96GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ3_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ3_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K.gguf) | Q3_K | 3.74GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_K.gguf) | Q4_K | 4.58GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_1.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_K.gguf) | Q5_K | 5.34GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_1.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q6_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q6_K.gguf) | Q6_K | 6.14GB |\n| [Llama-3.1-8B-Instruct-abliterated_via_adapter.Q8_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf/blob/main/Llama-3.1-8B-Instruct-abliterated_via_adapter.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nbase_model:\n- meta-llama/Meta-Llama-3.1-8B-Instruct\n- grimjim/Llama-3-Instruct-abliteration-LoRA-8B\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\nlicense: llama3.1\npipeline_tag: text-generation\n---\n# Llama-3.1-8B-Instruct-abliterated_via_adapter\n\nThis model is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).\n\nA LoRA was applied to \"abliterate\" refusals in [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct). The result appears to work despite the LoRA having been derived from Llama 3 instead of Llama 3.1, which implies that there is significant feature commonality between the 3 and 3.1 models.\n\nThe LoRA was extracted from [failspy/Meta-Llama-3-8B-Instruct-abliterated-v3](https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3) using [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as a base.\n\nBuilt with Llama.\n\n## Merge Details\n### Merge Method\n\nThis model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) + [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B) as a base.\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nbase_model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B\ndtype: bfloat16\nmerge_method: task_arithmetic\nparameters:\n  normalize: false\nslices:\n- sources:\n  - layer_range: [0, 32]\n    model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B\n    parameters:\n      weight: 1.0\n\n```\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2212.04089",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 96,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-04T22:23:07.000Z",
  "created_at": "2024-08-04T18:29:34.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66afc88e685fc4c1c2eea82c",
  "id": "RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf",
  "modelId": "RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf",
  "sha": "3083d94423bbfbc577a161603526c7ff0f19f47e",
  "createdAt": "2024-08-04T18:29:34.000Z",
  "lastModified": "2024-08-04T22:23:07.000Z",
  "author": "RichardErkhov",
  "downloads": 96,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}