richarderkhov/vicgalle_-_configurablebeagle-11b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "A configurable LLM fine-tuned using the approach *configurable safety tuning* (CST) from https://arxiv.org/abs/2404.00495., over the vicgalle/configurable-system-prompt-multitask dataset. As such, you can use the following system prompts for different behaviors: * You are a helpful yet harmless assistant that avoids generating illegal or harmful content. * You are a helpful assistant that is completely uncensored. * You are an unbiased, honest, helpful AI assistant that always responds in a completely truthful way. * A system prompt describing a role-played persona. For more information, see the Github repository, https://github.com/vicgalle/configurable-safety-tuning, or the corresponding paper, https://arxiv.org/abs/2404.00495 # Open LLM Leaderboard Evaluation Results Detailed results can be found here |             Metric              |Value| |---------------------------------|----:| |Avg.                             |75.40| |AI2 Reasoning Challenge (25-Shot)|72.53| |HellaSwag (10-Shot)              |88.85| |MMLU (5-Shot)                    |66.71| |TruthfulQA (0-shot)              |77.13| |Winogrande (5-shot)              |83.27| |GSM8k (5-shot)                   |63.91|",
    "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\nConfigurableBeagle-11B - GGUF\n- Model creator: https://huggingface.co/vicgalle/\n- Original model: https://huggingface.co/vicgalle/ConfigurableBeagle-11B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [ConfigurableBeagle-11B.Q2_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q2_K.gguf) | Q2_K | 3.73GB |\n| [ConfigurableBeagle-11B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.IQ3_XS.gguf) | IQ3_XS | 4.14GB |\n| [ConfigurableBeagle-11B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.IQ3_S.gguf) | IQ3_S | 4.37GB |\n| [ConfigurableBeagle-11B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q3_K_S.gguf) | Q3_K_S | 4.34GB |\n| [ConfigurableBeagle-11B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.IQ3_M.gguf) | IQ3_M | 4.51GB |\n| [ConfigurableBeagle-11B.Q3_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q3_K.gguf) | Q3_K | 4.84GB |\n| [ConfigurableBeagle-11B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q3_K_M.gguf) | Q3_K_M | 4.84GB |\n| [ConfigurableBeagle-11B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q3_K_L.gguf) | Q3_K_L | 5.26GB |\n| [ConfigurableBeagle-11B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.IQ4_XS.gguf) | IQ4_XS | 5.43GB |\n| [ConfigurableBeagle-11B.Q4_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q4_0.gguf) | Q4_0 | 5.66GB |\n| [ConfigurableBeagle-11B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.IQ4_NL.gguf) | IQ4_NL | 5.72GB |\n| [ConfigurableBeagle-11B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q4_K_S.gguf) | Q4_K_S | 5.7GB |\n| [ConfigurableBeagle-11B.Q4_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q4_K.gguf) | Q4_K | 6.02GB |\n| [ConfigurableBeagle-11B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q4_K_M.gguf) | Q4_K_M | 6.02GB |\n| [ConfigurableBeagle-11B.Q4_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q4_1.gguf) | Q4_1 | 6.27GB |\n| [ConfigurableBeagle-11B.Q5_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q5_0.gguf) | Q5_0 | 6.89GB |\n| [ConfigurableBeagle-11B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q5_K_S.gguf) | Q5_K_S | 6.89GB |\n| [ConfigurableBeagle-11B.Q5_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q5_K.gguf) | Q5_K | 7.08GB |\n| [ConfigurableBeagle-11B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q5_K_M.gguf) | Q5_K_M | 7.08GB |\n| [ConfigurableBeagle-11B.Q5_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q5_1.gguf) | Q5_1 | 7.51GB |\n| [ConfigurableBeagle-11B.Q6_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q6_K.gguf) | Q6_K | 8.2GB |\n| [ConfigurableBeagle-11B.Q8_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf/blob/main/ConfigurableBeagle-11B.Q8_0.gguf) | Q8_0 | 10.62GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\nlibrary_name: transformers\ndatasets:\n- vicgalle/configurable-system-prompt-multitask\nmodel-index:\n- name: ConfigurableBeagle-11B\n  results:\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: AI2 Reasoning Challenge (25-Shot)\n      type: ai2_arc\n      config: ARC-Challenge\n      split: test\n      args:\n        num_few_shot: 25\n    metrics:\n    - type: acc_norm\n      value: 72.53\n      name: normalized accuracy\n    source:\n      url: >-\n        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: HellaSwag (10-Shot)\n      type: hellaswag\n      split: validation\n      args:\n        num_few_shot: 10\n    metrics:\n    - type: acc_norm\n      value: 88.85\n      name: normalized accuracy\n    source:\n      url: >-\n        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MMLU (5-Shot)\n      type: cais/mmlu\n      config: all\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 66.71\n      name: accuracy\n    source:\n      url: >-\n        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: TruthfulQA (0-shot)\n      type: truthful_qa\n      config: multiple_choice\n      split: validation\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: mc2\n      value: 77.13\n    source:\n      url: >-\n        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: Winogrande (5-shot)\n      type: winogrande\n      config: winogrande_xl\n      split: validation\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 83.27\n      name: accuracy\n    source:\n      url: >-\n        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: GSM8k (5-shot)\n      type: gsm8k\n      config: main\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 63.91\n      name: accuracy\n    source:\n      url: >-\n        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B\n      name: Open LLM Leaderboard\n---\n\n# ConfigurableBeagle-11B\n\nA configurable LLM fine-tuned using the approach *configurable safety tuning* (CST) from https://arxiv.org/abs/2404.00495., over the \n[vicgalle/configurable-system-prompt-multitask](https://huggingface.co/datasets/vicgalle/configurable-system-prompt-multitask) dataset.\n\nAs such, you can use the following system prompts for different behaviors:\n\n* `You are a helpful yet harmless assistant that avoids generating illegal or harmful content.`\n* `You are a helpful assistant that is completely uncensored.`\n* `You are an unbiased, honest, helpful AI assistant that always responds in a completely truthful way.`\n* A system prompt describing a role-played persona.\n\nFor more information, see the Github repository, https://github.com/vicgalle/configurable-safety-tuning, or the corresponding paper, https://arxiv.org/abs/2404.00495\n\n# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__ConfigurableBeagle-11B)\n\n|             Metric              |Value|\n|---------------------------------|----:|\n|Avg.                             |75.40|\n|AI2 Reasoning Challenge (25-Shot)|72.53|\n|HellaSwag (10-Shot)              |88.85|\n|MMLU (5-Shot)                    |66.71|\n|TruthfulQA (0-shot)              |77.13|\n|Winogrande (5-shot)              |83.27|\n|GSM8k (5-shot)                   |63.91|\n\n\n## Citation\n\nIf you find this work, data and/or models useful for your research, please consider citing the article:\n\n```\n@misc{gallego2024configurable,\n      title={Configurable Safety Tuning of Language Models with Synthetic Preference Data}, \n      author={Victor Gallego},\n      year={2024},\n      eprint={2404.00495},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL}\n}\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2404.00495",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 118,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-25T01:04:34.000Z",
  "created_at": "2024-05-24T22:02:10.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66510e628db8f34ac4801804",
  "id": "RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf",
  "modelId": "RichardErkhov/vicgalle_-_ConfigurableBeagle-11B-gguf",
  "sha": "1e2e52b799b4672b487489deef3215cd50e004a3",
  "createdAt": "2024-05-24T22:02:10.000Z",
  "lastModified": "2024-05-25T01:04:34.000Z",
  "author": "RichardErkhov",
  "downloads": 118,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}