tripolskypetr/saiga_yandexgpt_8b_gguf overview

{
  "metadata": {},
  "card_data": {
    "datasets": [
      "IlyaGusev/saiga_scored",
      "IlyaGusev/saiga_preferences"
    ],
    "language": [
      "ru"
    ],
    "inference": false,
    "license": "other",
    "license_name": "yandexgpt-5-lite-8b-pretrain",
    "license_link": "LICENSE",
    "frontmatter": {
      "datasets": [
        "IlyaGusev/saiga_scored",
        "IlyaGusev/saiga_preferences"
      ],
      "language": [
        "ru"
      ],
      "inference": "false",
      "license": "other",
      "license_name": "yandexgpt-5-lite-8b-pretrain",
      "license_link": "LICENSE"
    },
    "hero_image_url": "",
    "summary": "Llama.cpp compatible versions of an original 8B model. Download one of the versions, for example saiga_yandexgpt_8b.Q4_K_M.gguf. `` wget https://huggingface.co/IlyaGusev/saiga_yandexgpt_8b_gguf/resolve/main/saiga_yandexgpt_8b.Q4_K_M.gguf ` Download interact_gguf.py ` https://raw.githubusercontent.com/IlyaGusev/saiga/refs/heads/main/scripts/interact_gguf.py ` How to run: ` pip install llama-cpp-python fire python3 interact_gguf.py saiga_yandexgpt_8b.Q4_K_M.gguf `` System requirements: * 9GB RAM for q8_0 and less for smaller quantizations",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ndatasets:\n- IlyaGusev/saiga_scored\n- IlyaGusev/saiga_preferences\nlanguage:\n- ru\ninference: false\nlicense: other\nlicense_name: yandexgpt-5-lite-8b-pretrain\nlicense_link: LICENSE\n---\n\nLlama.cpp compatible versions of an original [8B model](https://huggingface.co/IlyaGusev/saiga_yandexgpt_8b).\n\nDownload one of the versions, for example `saiga_yandexgpt_8b.Q4_K_M.gguf`.\n```\nwget https://huggingface.co/IlyaGusev/saiga_yandexgpt_8b_gguf/resolve/main/saiga_yandexgpt_8b.Q4_K_M.gguf\n```\n\nDownload [interact_gguf.py](https://raw.githubusercontent.com/IlyaGusev/saiga/refs/heads/main/scripts/interact_gguf.py)\n```\nhttps://raw.githubusercontent.com/IlyaGusev/saiga/refs/heads/main/scripts/interact_gguf.py\n```\n\nHow to run:\n```\npip install llama-cpp-python fire\n\npython3 interact_gguf.py saiga_yandexgpt_8b.Q4_K_M.gguf\n```\n\nSystem requirements:\n* 9GB RAM for q8_0 and less for smaller quantizations",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "ru",
    "dataset:IlyaGusev/saiga_scored",
    "dataset:IlyaGusev/saiga_preferences",
    "doi:10.57967/hf/6521",
    "license:other",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 124,
  "gated": false,
  "private": false,
  "last_modified": "2025-05-21T11:42:11.000Z",
  "created_at": "2025-05-19T17:01:04.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "682b63d0c0413a308222bd9c",
  "id": "tripolskypetr/saiga_yandexgpt_8b_gguf",
  "modelId": "tripolskypetr/saiga_yandexgpt_8b_gguf",
  "sha": "7e8bf8cda92a49f59802d87ca5ab4590a4d4d8a9",
  "createdAt": "2025-05-19T17:01:04.000Z",
  "lastModified": "2025-05-21T11:42:11.000Z",
  "author": "tripolskypetr",
  "downloads": 124,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 13
}