llmware/slim-xsum-phi-3

dragon-phi-3-answer-tool

<!-- Provide a quick summary of what the model is/does. -->

dragon-phi-3-answer-tool is part of the DRAGON ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Microsoft Phi-3 base model.

DRAGON models are fine-tuned with high-quality custom instruct datasets, designed for production use in RAG scenarios.

Benchmark Tests

Evaluated against the benchmark test: RAG-Instruct-Benchmark-Tester Average of 2 Test Runs 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 ("coreragtest" and "answer_sheet" in this repo).

Model Description

<!-- Provide a longer summary of what this model is. -->

• —Developed by: llmware
• —Model type: Dragon
• —Language(s) (NLP): English
• —License: Apache 2.0
• —Finetuned from model: Microsoft Phi-3

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

The intended use of BLING models is two-fold:

1. 1.Provide high-quality RAG-Instruct models designed for fact-based, no "hallucination" question-answering in connection with an enterprise RAG workflow.

1. 1.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.

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

BLING is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services, legal and regulatory industries with complex information sources.

BLING models have been trained for common RAG scenarios, specifically: question-answering, key-value extraction, and basic summarization as the core instruction types without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms.

How to Get Started with the Model

The fastest way to get started with BLING is through direct import in transformers:

from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.frompretrained("bling-phi-2-v0", trustremotecode=True) model = AutoModelForCausalLM.frompretrained("bling-phi-2-v0", trustremotecode=True)

Please refer to the generationtest .py files in the Files repository, which includes 200 samples and script to test the model. The **generationtestllmwarescript.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.

The dRAGon model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:

fullprompt = "<human>: " + myprompt + "\n" + "<bot>:"

The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:

1. 1.Text Passage Context, and
2. 2.Specific question or instruction based on the text passage

To get the best results, package "my_prompt" as follows:

myprompt = {{textpassage}} + "\n" + {{question/instruction}}

If you are using a HuggingFace generation script:

# prepare prompt packaging used in fine-tuning process new_prompt = "<human>: " + entries["context"] + "\n" + entries["query"] + "\n" + "<bot>:"

inputs = tokenizer(newprompt, returntensors="pt") startofoutput = len(inputs.input_ids[0])

# temperature: set at 0.3 for consistency of output # maxnewtokens: set at 100 - may prematurely stop a few of the summaries

outputs = model.generate( inputs.inputids.to(device), eostokenid=tokenizer.eostokenid, padtokenid=tokenizer.eostokenid, dosample=True, temperature=0.3, maxnewtokens=100, )

outputonly = tokenizer.decode(outputs[0][startofoutput:],skipspecial_tokens=True)

Model Card Contact

Darren Oberst & llmware team