quantfactory/arliai-llama-3-8b-cumulus-v1.0-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "llama3",
    "pipeline_tag": "text-generation",
    "base_model": "OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0",
    "frontmatter": {
      "license": "llama3",
      "pipeline_tag": "text-generation",
      "base_model": "OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0"
    },
    "hero_image_url": "",
    "summary": "This is quantized version of OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0 created using llama.cpp # Model Description Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct This is release v1.0 of Awanllm Cumulus series of models that aim to be uncensored and have zero refusals and zero warnings. This model should be good for general use cases as the OG Llama 3 8B model but it should be especially better for story writing or RP use cases. It is the most uncensored yet, thanks to using https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 as the base model. In terms of reasoning and intelligence, this model is probably a bit worse than the OG Meta Llama 3 8B Instruct because of the decensoring. However we believe it is worth it for the decensoring, as even with jailbreak prompts Llama 3 8B Instruct will never get remotely close to this model. Best practices: Training: Instruct format: `` system {{ system_prompt }}user {{ user_message_1 }}assistant {{ model_answer_1 }}user {{ user_message_2 }}assistant ``",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: llama3\npipeline_tag: text-generation\nbase_model: OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0\n---\n\n# QuantFactory/ArliAI-Llama-3-8B-Cumulus-v1.0-GGUF\nThis is quantized version of [OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0](https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0) created using llama.cpp\n\n# Model Description\nBased on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement:\nhttps://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct\n\n\nThis is release v1.0 of Awanllm Cumulus series of models that aim to be uncensored and have zero refusals and zero warnings. \n\nThis model should be good for general use cases as the OG Llama 3 8B model but it should be especially better for story writing or RP use cases.\n\nIt is the most uncensored yet, thanks to using https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 as the base model.\n\n\nIn terms of reasoning and intelligence, this model is probably a bit worse than the OG Meta Llama 3 8B Instruct because of the decensoring. However we believe it is worth it for the decensoring, as even with jailbreak prompts Llama 3 8B Instruct will never get remotely close to this model.\n\n\nBest practices:\n  - Be precise and explain what you want the model to do. It has less base \"personality\" than the OG model but it will act however you tell it to.\n  - This model works best with system prompts that tells it that it is the character, instead of telling it to act as a character. \n\n\nTraining:\n- Full 8192 sequence length.\n- Training duration is around 4 days on an RTX 4090, using 4-bit loading and Qlora 64-rank 64-alpha resulting in ~2% trainable weights.\n\n\nInstruct format:\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{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-generation",
    "base_model:OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0",
    "base_model:quantized:OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0",
    "license:llama3",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 316,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-14T17:00:58.000Z",
  "created_at": "2024-07-13T12:54:48.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "66927918609e838ebd9a388e",
  "id": "QuantFactory/ArliAI-Llama-3-8B-Cumulus-v1.0-GGUF",
  "modelId": "QuantFactory/ArliAI-Llama-3-8B-Cumulus-v1.0-GGUF",
  "sha": "c0a93afa0be6912606e57e3e2cb16d905a266aa7",
  "createdAt": "2024-07-13T12:54:48.000Z",
  "lastModified": "2024-07-14T17:00:58.000Z",
  "author": "QuantFactory",
  "downloads": 316,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 16
}