llmware/bling-phi-3-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "inference": false,
    "frontmatter": {
      "license": "apache-2.0",
      "inference": "false"
    },
    "hero_image_url": "",
    "summary": "bling-phi-3-gguf is part of the BLING (\"Best Little Instruct No-GPU\") model series, RAG-instruct trained for fact-based question-answering use cases on top of a Microsoft Phi-3 base model. ### Benchmark Tests Evaluated against the benchmark test:   RAG-Instruct-Benchmark-Tester 1 Test Run (with temperature = 0.0 and sample = False) with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations. --**Accuracy Score**:  **100.0** correct out of 100 --Not Found Classification:  95.0% --Boolean:  97.5% --Math/Logic:  80.0% --Complex Questions (1-5):  4 (Above Average - multiple-choice, causal) --Summarization Quality (1-5):  4 (Above Average) --Hallucinations:  No hallucinations observed in test runs. For test run results (and good indicator of target use cases), please see the files (\"core_rag_test\" and \"answer_sheet\" in this repo). Note: compare results with bling-phi-2, and dragon-mistral-7b. ### Model Description",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0  \ninference: false  \n---\n\n# bling-phi-3-gguf\n\n<!-- Provide a quick summary of what the model is/does. -->\n\nbling-phi-3-gguf is part of the BLING (\"Best Little Instruct No-GPU\") model series, RAG-instruct trained for fact-based question-answering use cases on top of a Microsoft Phi-3 base model.\n\n\n### Benchmark Tests  \n\nEvaluated against the benchmark test:   [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester)  \n1 Test Run (with temperature = 0.0 and sample = False) with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations.  \n\n--**Accuracy Score**:  **100.0** correct out of 100  \n--Not Found Classification:  95.0%  \n--Boolean:  97.5%  \n--Math/Logic:  80.0%  \n--Complex Questions (1-5):  4 (Above Average - multiple-choice, causal)  \n--Summarization Quality (1-5):  4 (Above Average)  \n--Hallucinations:  No hallucinations observed in test runs.  \n\nFor test run results (and good indicator of target use cases), please see the files (\"core_rag_test\" and \"answer_sheet\" in this repo).  \n\nNote: compare results with [bling-phi-2](https://www.huggingface.co/llmware/bling-phi-2-v0), and [dragon-mistral-7b](https://www.huggingface.co/llmware/dragon-mistral-7b-v0).  \n\n\n### Model Description\n\n<!-- Provide a longer summary of what this model is. -->\n\n- **Developed by:** llmware\n- **Model type:** bling-rag-instruct \n- **Language(s) (NLP):** English\n- **License:** Apache 2.0\n- **Finetuned from model:** Microsoft Phi-3\n\n## Uses\n\n<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->\n\nThe intended use of BLING models is two-fold:\n\n1.  Provide high-quality RAG-Instruct models designed for fact-based, no \"hallucination\" question-answering in connection with an enterprise RAG workflow.\n\n2.  BLING models are fine-tuned on top of leading base foundation models, generally in the 1-3B+ range, and purposefully rolled-out across multiple base models to provide choices and \"drop-in\" replacements for RAG specific use cases.\n\n\n### Direct Use\n\n<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->\n\nBLING is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services,\nlegal and regulatory industries with complex information sources.  \n\nBLING models have been trained for common RAG scenarios, specifically:   question-answering, key-value extraction, and basic summarization as the core instruction types\nwithout the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.\n\n\n## Bias, Risks, and Limitations\n\n<!-- This section is meant to convey both technical and sociotechnical limitations. -->\n\nBLING models are designed to operate with grounded sources, e.g., inclusion of a context passage in the prompt, and will not yield consistent or positive results if open-context prompting in which you are looking for the model to draw upon potential background knowledge of the world - in fact, it is likely that the BLING will respond with a simple \"Not Found.\" to an open context query.  \n\nAny model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms.\n\n\n## How to Get Started with the Model\n\nTo pull the model via API:  \n\n    from huggingface_hub import snapshot_download           \n    snapshot_download(\"llmware/bling-phi-3-gguf\", local_dir=\"/path/on/your/machine/\", local_dir_use_symlinks=False)  \n    \nLoad in your favorite GGUF inference engine, or try with llmware as follows:\n\n    from llmware.models import ModelCatalog  \n    \n    # to load the model and make a basic inference\n    model = ModelCatalog().load_model(\"llmware/bling-phi-3-gguf\", temperature=0.0, sample=False)\n    response = model.inference(query, add_context=text_sample)  \n\nDetails on the prompt wrapper and other configurations are on the config.json file in the files repository.  \n\n## Model Card Contact\n\nDarren Oberst & llmware team\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "phi-3",
    "license:apache-2.0",
    "region:us",
    "conversational"
  ],
  "likes": 15,
  "downloads": 194,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-02T20:29:03.000Z",
  "created_at": "2024-04-24T17:04:40.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "66293ba87a1112fd614f4cbe",
  "id": "llmware/bling-phi-3-gguf",
  "modelId": "llmware/bling-phi-3-gguf",
  "sha": "0f7807821930280fa929dc2d2403ead0a98cc1c3",
  "createdAt": "2024-04-24T17:04:40.000Z",
  "lastModified": "2024-05-02T20:29:03.000Z",
  "author": "llmware",
  "downloads": 194,
  "likes": 15,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 7
}