richarderkhov/edentns_-_datavortextl-1.1b-v0.1-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "./DataVortex.png",
    "summary": "",
    "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\nDataVortexTL-1.1B-v0.1 - GGUF\n- Model creator: https://huggingface.co/Edentns/\n- Original model: https://huggingface.co/Edentns/DataVortexTL-1.1B-v0.1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [DataVortexTL-1.1B-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q2_K.gguf) | Q2_K | 0.4GB |\n| [DataVortexTL-1.1B-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.IQ3_XS.gguf) | IQ3_XS | 0.44GB |\n| [DataVortexTL-1.1B-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.IQ3_S.gguf) | IQ3_S | 0.47GB |\n| [DataVortexTL-1.1B-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q3_K_S.gguf) | Q3_K_S | 0.47GB |\n| [DataVortexTL-1.1B-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.IQ3_M.gguf) | IQ3_M | 0.48GB |\n| [DataVortexTL-1.1B-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q3_K.gguf) | Q3_K | 0.51GB |\n| [DataVortexTL-1.1B-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q3_K_M.gguf) | Q3_K_M | 0.51GB |\n| [DataVortexTL-1.1B-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q3_K_L.gguf) | Q3_K_L | 0.55GB |\n| [DataVortexTL-1.1B-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.IQ4_XS.gguf) | IQ4_XS | 0.57GB |\n| [DataVortexTL-1.1B-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q4_0.gguf) | Q4_0 | 0.59GB |\n| [DataVortexTL-1.1B-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.IQ4_NL.gguf) | IQ4_NL | 0.6GB |\n| [DataVortexTL-1.1B-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q4_K_S.gguf) | Q4_K_S | 0.6GB |\n| [DataVortexTL-1.1B-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q4_K.gguf) | Q4_K | 0.62GB |\n| [DataVortexTL-1.1B-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q4_K_M.gguf) | Q4_K_M | 0.62GB |\n| [DataVortexTL-1.1B-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q4_1.gguf) | Q4_1 | 0.65GB |\n| [DataVortexTL-1.1B-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q5_0.gguf) | Q5_0 | 0.71GB |\n| [DataVortexTL-1.1B-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q5_K_S.gguf) | Q5_K_S | 0.71GB |\n| [DataVortexTL-1.1B-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q5_K.gguf) | Q5_K | 0.73GB |\n| [DataVortexTL-1.1B-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q5_K_M.gguf) | Q5_K_M | 0.73GB |\n| [DataVortexTL-1.1B-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q5_1.gguf) | Q5_1 | 0.77GB |\n| [DataVortexTL-1.1B-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q6_K.gguf) | Q6_K | 0.84GB |\n| [DataVortexTL-1.1B-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf/blob/main/DataVortexTL-1.1B-v0.1.Q8_0.gguf) | Q8_0 | 1.09GB |\n\n\n\n\nOriginal model description:\n---\ntags:\n    - text-generation\nlicense: cc-by-nc-sa-4.0\nlanguage:\n    - ko\nbase_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0\npipeline_tag: text-generation\ndatasets:\n    - beomi/KoAlpaca-v1.1a\n    - jojo0217/korean_rlhf_dataset\n    - kyujinpy/OpenOrca-KO\n    - nlpai-lab/kullm-v2\nwidget:\n   - text: >\n       <|system|>\n \n       You are a chatbot who answers User's questions.\n \n       <|user|>\n \n       대한민국의 수도는 어디야?\n \n       <|assistant|>\n---\n\n# **DataVortexTL-1.1B-v0.1**\n\n<img src=\"./DataVortex.png\" alt=\"DataVortex\" style=\"height: 8em;\">\n\n## Our Team\n\n| Research & Engineering | Product Management |\n| :--------------------: | :----------------: |\n|     Kwangseok Yang     |   Seunghyun Choi   |\n|     Jeongwon Choi      |    Hyoseok Choi    |\n\n## **Model Details**\n\n### **Base Model**\n\n[TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)\n\n### **Trained On**\n\n-   **OS**: Ubuntu 20.04\n-   **GPU**: H100 80GB 1ea\n-   **transformers**: v4.36.2\n\n### **Dataset**\n\n-   [beomi/KoAlpaca-v1.1a](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a)\n-   [jojo0217/korean_rlhf_dataset](https://huggingface.co/datasets/jojo0217/korean_rlhf_dataset)\n-   [kyujinpy/OpenOrca-KO](https://huggingface.co/datasets/kyujinpy/OpenOrca-KO)\n-   [nlpai-lab/kullm-v2](https://huggingface.co/datasets/nlpai-lab/kullm-v2)\n\n### **Instruction format**\n\nIt follows **TinyLlama** format.\n\nE.g.\n\n```python\ntext = \"\"\"\\\n<|system|>\n당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.</s>\n<|user|>\n대한민국의 수도는 어디야?</s>\n<|assistant|>\n대한민국의 수도는 서울입니다.</s>\n<|user|>\n서울 인구는 총 몇 명이야?</s>\n\"\"\"\n```\n\n## **Model Benchmark**\n\n### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**\n\n| Task             |         0-shot |         5-shot |        10-shot |      50-shot |\n| :--------------- | -------------: | -------------: | -------------: | -----------: |\n| kobest_boolq     |       0.334282 |       0.516446 |       0.500478 |     0.498941 |\n| kobest_copa      |       0.515061 |       0.504321 |       0.492927 |      0.50809 |\n| kobest_hellaswag |        0.36253 |       0.357733 |       0.355873 |     0.376502 |\n| kobest_sentineg  |       0.481146 |       0.657411 |       0.687417 |     0.635703 |\n| **Average**      | **0.42325475** | **0.50897775** | **0.50917375** | **0.504809** |\n\n### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**\n\n| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |\n| ------: | -----: | -----------: | ------: | ------------: | --------------: |\n|    31.5 |  25.26 |        33.53 |   24.56 |         43.34 |           30.81 |\n\n## **Implementation Code**\n\nThis model contains the chat_template instruction format.  \nYou can use the code below.\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\ndevice = \"cuda\" # the device to load the model onto\n\nmodel = AutoModelForCausalLM.from_pretrained(\"Edentns/DataVortexTL-1.1B-v0.1\")\ntokenizer = AutoTokenizer.from_pretrained(\"Edentns/DataVortexTL-1.1B-v0.1\")\n\nmessages = [\n    {\"role\": \"system\", \"content\": \"당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.\"},\n    {\"role\": \"user\", \"content\": \"대한민국의 수도는 어디야?\"},\n    {\"role\": \"assistant\", \"content\": \"대한민국의 수도는 서울입니다.\"},\n    {\"role\": \"user\", \"content\": \"서울 인구는 총 몇 명이야?\"}\n]\n\nencodeds = tokenizer.apply_chat_template(messages, return_tensors=\"pt\")\n\nmodel_inputs = encodeds.to(device)\nmodel.to(device)\n\ngenerated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)\ndecoded = tokenizer.batch_decode(generated_ids)\nprint(decoded[0])\n```\n\n## **License**\n\nThe model is licensed under the [cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license, which allows others to copy, modify, and share the work non-commercially, as long as they give appropriate credit and distribute any derivative works under the same license.\n\n<div align=\"center\">\n    <a href=\"https://edentns.com/\">\n        <img src=\"./Logo.png\" alt=\"Logo\" style=\"height: 3em;\">\n    </a>\n</div>\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 226,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-02T17:05:51.000Z",
  "created_at": "2024-07-02T16:54:57.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "668430e152453d2e9c691f04",
  "id": "RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf",
  "modelId": "RichardErkhov/Edentns_-_DataVortexTL-1.1B-v0.1-gguf",
  "sha": "ad333b59fe6fc10fc9a80c450eec05aa438623a7",
  "createdAt": "2024-07-02T16:54:57.000Z",
  "lastModified": "2024-07-02T17:05:51.000Z",
  "author": "RichardErkhov",
  "downloads": 226,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}