richarderkhov/azure99_-_blossom-v5.1-34b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "💻Github • 🚀Blossom Chat Demo ### Introduction Blossom is a conversational large language model, fine-tuned on the Blossom Orca/Wizard/Chat/Math mixed dataset based on the Yi-1.5-34B pre-trained model. Blossom possesses robust general capabilities and context comprehension. Additionally, the high-quality Chinese and English datasets used for training have been made open source. Training was conducted in two stages. The first stage used 40K Wizard, 40K Orca, 10K Math single-turn instruction datasets, training for 1 epoch; the second stage used 10K Blossom chat multi-turn dialogue dataset, and 10% randomly sampled data from the first stage, training for 3 epochs. ### Inference Inference is performed in the form of dialogue continuation. Single-turn dialogue `` A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions. |Human|: hello |Bot|: ` Multi-turn dialogue ` A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions. |Human|: hello |Bot|: Hello! How can I assist you today? |Human|: Generate a random number using python |Bot|: ` Note: At the end of the Bot's output in the historical conversation, append a `.",
    "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-v5.1-34b - GGUF\n- Model creator: https://huggingface.co/Azure99/\n- Original model: https://huggingface.co/Azure99/blossom-v5.1-34b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [blossom-v5.1-34b.Q2_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q2_K.gguf) | Q2_K | 11.94GB |\n| [blossom-v5.1-34b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.IQ3_XS.gguf) | IQ3_XS | 13.26GB |\n| [blossom-v5.1-34b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.IQ3_S.gguf) | IQ3_S | 13.99GB |\n| [blossom-v5.1-34b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q3_K_S.gguf) | Q3_K_S | 13.93GB |\n| [blossom-v5.1-34b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.IQ3_M.gguf) | IQ3_M | 14.5GB |\n| [blossom-v5.1-34b.Q3_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q3_K.gguf) | Q3_K | 15.51GB |\n| [blossom-v5.1-34b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q3_K_M.gguf) | Q3_K_M | 15.51GB |\n| [blossom-v5.1-34b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q3_K_L.gguf) | Q3_K_L | 16.89GB |\n| [blossom-v5.1-34b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.IQ4_XS.gguf) | IQ4_XS | 17.36GB |\n| [blossom-v5.1-34b.Q4_0.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q4_0.gguf) | Q4_0 | 18.13GB |\n| [blossom-v5.1-34b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.IQ4_NL.gguf) | IQ4_NL | 18.3GB |\n| [blossom-v5.1-34b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q4_K_S.gguf) | Q4_K_S | 18.25GB |\n| [blossom-v5.1-34b.Q4_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q4_K.gguf) | Q4_K | 19.24GB |\n| [blossom-v5.1-34b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q4_K_M.gguf) | Q4_K_M | 19.24GB |\n| [blossom-v5.1-34b.Q4_1.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q4_1.gguf) | Q4_1 | 20.1GB |\n| [blossom-v5.1-34b.Q5_0.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q5_0.gguf) | Q5_0 | 22.08GB |\n| [blossom-v5.1-34b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q5_K_S.gguf) | Q5_K_S | 22.08GB |\n| [blossom-v5.1-34b.Q5_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q5_K.gguf) | Q5_K | 22.65GB |\n| [blossom-v5.1-34b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q5_K_M.gguf) | Q5_K_M | 22.65GB |\n| [blossom-v5.1-34b.Q5_1.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q5_1.gguf) | Q5_1 | 24.05GB |\n| [blossom-v5.1-34b.Q6_K.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q6_K.gguf) | Q6_K | 26.28GB |\n| [blossom-v5.1-34b.Q8_0.gguf](https://huggingface.co/RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf/blob/main/blossom-v5.1-34b.Q8_0.gguf) | Q8_0 | 34.03GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\ndatasets:\n- Azure99/blossom-chat-v3\n- Azure99/blossom-math-v4\n- Azure99/blossom-wizard-v3\n- Azure99/blossom-orca-v3\nlanguage:\n- zh\n- en\n---\n# **BLOSSOM-v5.1-34b**\n\n[💻Github](https://github.com/Azure99/BlossomLM) • [🚀Blossom Chat Demo](https://blossom-chat.com/)\n\n### Introduction\n\nBlossom is a conversational large language model, fine-tuned on the Blossom Orca/Wizard/Chat/Math mixed dataset based on the Yi-1.5-34B pre-trained model. Blossom possesses robust general capabilities and context comprehension. Additionally, the high-quality Chinese and English datasets used for training have been made open source.\n\nTraining was conducted in two stages. The first stage used 40K Wizard, 40K Orca, 10K Math single-turn instruction datasets, training for 1 epoch; the second stage used 10K Blossom chat multi-turn dialogue dataset, and 10% randomly sampled data from the first stage, training for 3 epochs.\n\n### Inference\n\nInference is performed in the form of dialogue continuation.\n\nSingle-turn dialogue\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|: hello\n|Bot|: \n```\n\nMulti-turn dialogue\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|: hello\n|Bot|: Hello! How can I assist you today?<|endoftext|>\n|Human|: Generate a random number using python\n|Bot|: \n```\n\nNote: At the end of the Bot's output in the historical conversation, append a `<|endoftext|>`.\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 121,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-17T01:18:56.000Z",
  "created_at": "2024-09-16T09:48:11.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66e7fedbf0053c645b821657",
  "id": "RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf",
  "modelId": "RichardErkhov/Azure99_-_blossom-v5.1-34b-gguf",
  "sha": "997f5e5b663755d4396cb4ea4e9715104326f63b",
  "createdAt": "2024-09-16T09:48:11.000Z",
  "lastModified": "2024-09-17T01:18:56.000Z",
  "author": "RichardErkhov",
  "downloads": 121,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}