richarderkhov/sethuiyer_-_aika-7b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://huggingface.co/sethuiyer/Aika-7B/resolve/main/aika.webp",
    "summary": "Aika is a language model constructed using the DARE TIES merge method using mitultiwari/mistral-7B-instruct-dpo as a base. Aika is designed to interact with users in a way that feels natural and human-like, to solve problems and answer questions with a high degree of accuracy and truthfulness, and to engage in creative and logical tasks with proficiency. ### Models Merged The following models were included in the merge: * SanjiWatsuki/Silicon-Maid-7B * Guilherme34/Samantha-v2 * jan-hq/stealth-v1.3 * senseable/WestLake-7B-v2 The base model is Mistral-7Bv0.1 fine tuned on Anthropic/hh-rlhf. ### Why? Combine them all !img Source You get Aika - a considerate, personal digital assistant. ### Configuration Please check mergekit_config.yml for the merge config. # Open LLM Leaderboard Evaluation Results Detailed results can be found here |             Metric              |Value| |---------------------------------|----:| |Avg.                             |59.25| |AI2 Reasoning Challenge (25-Shot)|65.36| |HellaSwag (10-Shot)              |81.49| |MMLU (5-Shot)                    |53.91| |TruthfulQA (0-shot)              |51.22| |Winogrande (5-shot)              |77.74| |GSM8k (5-shot)                   |25.78|",
    "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\nAika-7B - GGUF\n- Model creator: https://huggingface.co/sethuiyer/\n- Original model: https://huggingface.co/sethuiyer/Aika-7B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Aika-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q2_K.gguf) | Q2_K | 2.53GB |\n| [Aika-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [Aika-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [Aika-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [Aika-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [Aika-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q3_K.gguf) | Q3_K | 3.28GB |\n| [Aika-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [Aika-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [Aika-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [Aika-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [Aika-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [Aika-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [Aika-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q4_K.gguf) | Q4_K | 4.07GB |\n| [Aika-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [Aika-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [Aika-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [Aika-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [Aika-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q5_K.gguf) | Q5_K | 4.78GB |\n| [Aika-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [Aika-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [Aika-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q6_K.gguf) | Q6_K | 5.53GB |\n| [Aika-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/sethuiyer_-_Aika-7B-gguf/blob/main/Aika-7B.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\nlanguage:\n- en\nlicense: cc\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\ndatasets:\n- Anthropic/hh-rlhf\nbase_model:\n- SanjiWatsuki/Silicon-Maid-7B\n- Guilherme34/Samantha-v2\n- jan-hq/stealth-v1.3\n- mitultiwari/mistral-7B-instruct-dpo\n- senseable/WestLake-7B-v2\nmodel-index:\n- name: sethuiyer/Aika-7B\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: 65.36\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B\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: 81.49\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B\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: 53.91\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B\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: 51.22\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B\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: 77.74\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B\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: 25.78\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B\n      name: Open LLM Leaderboard\n---\n# Aika-7B\n\n<p align=\"center\">\n  <img src=\"https://huggingface.co/sethuiyer/Aika-7B/resolve/main/aika.webp\" height=\"128px\" alt=\"Aika\">\n</p>\n\nAika is a language model constructed using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mitultiwari/mistral-7B-instruct-dpo](https://huggingface.co/mitultiwari/mistral-7B-instruct-dpo) as a base. Aika is designed to interact with users in a way that feels natural and human-like, to solve problems and answer questions with a high degree of accuracy and truthfulness, and to engage in creative and logical tasks with proficiency. \n\n### Models Merged\n\nThe following models were included in the merge:\n* [SanjiWatsuki/Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B)\n* [Guilherme34/Samantha-v2](https://huggingface.co/Guilherme34/Samantha-v2)\n* [jan-hq/stealth-v1.3](https://huggingface.co/jan-hq/stealth-v1.3)\n* [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2)\n\nThe base model is Mistral-7Bv0.1 fine tuned on [Anthropic/hh-rlhf](https://huggingface.co/datasets/Anthropic/hh-rlhf). \n\n### Why?\n- **Base model tuned on Anthropic RLHF dataset**: Safe AI as a base model, to balance the uncensored model below.\n- **Silicon-Maid-7B**: Boasts excellent multi-turn conversational skills and logical coherence, ensuring smooth interactions.\n- **Samantha-V2**: Offers empathy and human-like responses, equipped with programmed \"self-awareness\" for a more personalized experience.\n- **Stealth-V1.3**: Known for enhancing performance in merges when integrated as a component, optimizing Aika's functionality.\n- **WestLake-7B-V2**: Sets a high benchmark for emotional intelligence (EQ) and excels in creative writing, enhancing Aika's ability to understand and respond to your needs.\n\nCombine them all \n![img](https://huggingface.co/sethuiyer/Aika-7B/resolve/main/hoho.webp)\n\n[Source](https://powerpuffgirls.fandom.com/wiki/The_Powerpuff_Girls_theme_song?file=Professor_Utonium_Mixing_Stew.png)\n\nYou get Aika - a considerate, personal digital assistant.\n\n### Configuration\n\nPlease check [mergekit_config.yml](https://huggingface.co/sethuiyer/Aika-7B/blob/main/mergekit_config.yml) for the merge config.\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_sethuiyer__Aika-7B)\n\n|             Metric              |Value|\n|---------------------------------|----:|\n|Avg.                             |59.25|\n|AI2 Reasoning Challenge (25-Shot)|65.36|\n|HellaSwag (10-Shot)              |81.49|\n|MMLU (5-Shot)                    |53.91|\n|TruthfulQA (0-shot)              |51.22|\n|Winogrande (5-shot)              |77.74|\n|GSM8k (5-shot)                   |25.78|\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2311.03099",
    "arxiv:2306.01708",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 233,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-06T11:53:34.000Z",
  "created_at": "2024-09-06T04:56:06.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66da8b66e781122aae63c1a8",
  "id": "RichardErkhov/sethuiyer_-_Aika-7B-gguf",
  "modelId": "RichardErkhov/sethuiyer_-_Aika-7B-gguf",
  "sha": "1b15f1c680013d389c763ce90bd51189b843f1fc",
  "createdAt": "2024-09-06T04:56:06.000Z",
  "lastModified": "2024-09-06T11:53:34.000Z",
  "author": "RichardErkhov",
  "downloads": 233,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}