richarderkhov/azure99_-_blossom-v4-qwen1_5-7b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "💻Github • 🚀Blossom Chat Demo ### 介绍 Blossom是一个对话式语言模型，基于Qwen1.5-7B预训练模型，在Blossom Orca/Wizard/Chat/Math混合数据集上进行指令精调得来。Blossom拥有强大的通用能力及上下文理解能力，此外，训练使用的高质量中英文数据集也进行了开源。 训练分为两阶段，第一阶段使用100K Wizard、100K Orca、20K Math单轮指令数据集，训练1个epoch；第二阶段使用50K Blossom chat多轮对话数据集、以及上一阶段中随机采样2%的数据，训练3个epoch。 ### 推理 推理采用对话续写的形式。 单轮对话 `` A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions. |Human|: 你好 |Bot|: ` 多轮对话 ` A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions. |Human|: 你好 |Bot|: 你好，有什么我能帮助你的？ |Human|: 介绍下中国的首都吧 |Bot|: `` 注意：在历史对话的Bot输出结尾，拼接一个<|endoftext|>",
    "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\nblossom-v4-qwen1_5-7b - GGUF\n- Model creator: https://huggingface.co/Azure99/\n- Original model: https://huggingface.co/Azure99/blossom-v4-qwen1_5-7b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [blossom-v4-qwen1_5-7b.Q2_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q2_K.gguf) | Q2_K | 2.89GB |\n| [blossom-v4-qwen1_5-7b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.IQ3_XS.gguf) | IQ3_XS | 3.18GB |\n| [blossom-v4-qwen1_5-7b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.IQ3_S.gguf) | IQ3_S | 3.32GB |\n| [blossom-v4-qwen1_5-7b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q3_K_S.gguf) | Q3_K_S | 3.32GB |\n| [blossom-v4-qwen1_5-7b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.IQ3_M.gguf) | IQ3_M | 3.48GB |\n| [blossom-v4-qwen1_5-7b.Q3_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q3_K.gguf) | Q3_K | 3.65GB |\n| [blossom-v4-qwen1_5-7b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q3_K_M.gguf) | Q3_K_M | 3.65GB |\n| [blossom-v4-qwen1_5-7b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q3_K_L.gguf) | Q3_K_L | 3.93GB |\n| [blossom-v4-qwen1_5-7b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.IQ4_XS.gguf) | IQ4_XS | 4.02GB |\n| [blossom-v4-qwen1_5-7b.Q4_0.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q4_0.gguf) | Q4_0 | 4.2GB |\n| [blossom-v4-qwen1_5-7b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.IQ4_NL.gguf) | IQ4_NL | 4.22GB |\n| [blossom-v4-qwen1_5-7b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q4_K_S.gguf) | Q4_K_S | 4.23GB |\n| [blossom-v4-qwen1_5-7b.Q4_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q4_K.gguf) | Q4_K | 4.44GB |\n| [blossom-v4-qwen1_5-7b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q4_K_M.gguf) | Q4_K_M | 4.44GB |\n| [blossom-v4-qwen1_5-7b.Q4_1.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q4_1.gguf) | Q4_1 | 4.62GB |\n| [blossom-v4-qwen1_5-7b.Q5_0.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q5_0.gguf) | Q5_0 | 5.03GB |\n| [blossom-v4-qwen1_5-7b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q5_K_S.gguf) | Q5_K_S | 5.03GB |\n| [blossom-v4-qwen1_5-7b.Q5_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q5_K.gguf) | Q5_K | 5.15GB |\n| [blossom-v4-qwen1_5-7b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q5_K_M.gguf) | Q5_K_M | 5.15GB |\n| [blossom-v4-qwen1_5-7b.Q5_1.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q5_1.gguf) | Q5_1 | 5.44GB |\n| [blossom-v4-qwen1_5-7b.Q6_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q6_K.gguf) | Q6_K | 5.91GB |\n| [blossom-v4-qwen1_5-7b.Q8_0.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf/blob/main/blossom-v4-qwen1_5-7b.Q8_0.gguf) | Q8_0 | 7.65GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\ndatasets:\n- Azure99/blossom-chat-v2\n- Azure99/blossom-math-v3\n- Azure99/blossom-wizard-v2\n- Azure99/blossom-orca-v2\nlanguage:\n- zh\n- en\npipeline_tag: text-generation\n---\n# **BLOSSOM-v4-qwen1_5-7b**\n\n[💻Github](https://github.com/Azure99/BlossomLM) • [🚀Blossom Chat Demo](https://blossom-chat.com/)\n\n### 介绍\n\nBlossom是一个对话式语言模型，基于Qwen1.5-7B预训练模型，在Blossom Orca/Wizard/Chat/Math混合数据集上进行指令精调得来。Blossom拥有强大的通用能力及上下文理解能力，此外，训练使用的高质量中英文数据集也进行了开源。\n\n训练分为两阶段，第一阶段使用100K Wizard、100K Orca、20K Math单轮指令数据集，训练1个epoch；第二阶段使用50K Blossom chat多轮对话数据集、以及上一阶段中随机采样2%的数据，训练3个epoch。\n\n### 推理\n\n推理采用对话续写的形式。\n\n单轮对话\n\n```\nA chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.\n|Human|: 你好\n|Bot|: \n```\n\n多轮对话\n\n```\nA chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.\n|Human|: 你好\n|Bot|: 你好，有什么我能帮助你的？<|endoftext|>\n|Human|: 介绍下中国的首都吧\n|Bot|: \n```\n\n注意：在历史对话的Bot输出结尾，拼接一个&lt;|endoftext|&gt;\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 287,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-08T10:24:07.000Z",
  "created_at": "2024-09-08T03:45:26.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66dd1dd62b8718d1749b49c5",
  "id": "RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf",
  "modelId": "RichardErkhov/Azure99_-_blossom-v4-qwen1_5-7b-gguf",
  "sha": "c04b251a6b74085f8e42f4d62e9ee2f9ba5d2b82",
  "createdAt": "2024-09-08T03:45:26.000Z",
  "lastModified": "2024-09-08T10:24:07.000Z",
  "author": "RichardErkhov",
  "downloads": 287,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}