llmware / bling-phi-2-v0

Model Card for Model ID

bling-phi-2-v0 is part of the BLING ("Best Little Instruct No GPU Required ...") model series, RAG-instruct trained on top of a Microsoft Phi-2B base model.

BLING models are fine-tuned with high-quality custom instruct datasets, designed for rapid prototyping in RAG scenarios.

For models with comparable size and performance in RAG deployments, please see:

bling-stable-lm-3b-4e1t-v0
bling-sheared-llama-2.7b-0.1
bling-red-pajamas-3b-0.1

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 : 93.0 correct out of 100
--Not Found Classification: 95.0%
--Boolean: 85.0%
--Math/Logic: 82.5%
--Complex Questions (1-5): 3 (Above Average - multiple-choice, causal)
--Summarization Quality (1-5): 3 (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).

Model Description

• Developed by: llmware
• Model type: Phi-2B
• Language(s) (NLP): English
• License: Apache 2.0
• Finetuned from model: Microsoft Phi-2B-Base

Uses

The intended use of BLING models is two-fold:

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

2. 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

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

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.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  
model = AutoModelForCausalLM.from_pretrained("bling-phi-2-v0", trust_remote_code=True)  

Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model. The generation_test_llmware_script.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:

full_prompt = "<human>: " + my_prompt + "\n" + "<bot>:"

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

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

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

my_prompt = {{text_passage}} + "\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(new_prompt, return_tensors="pt")  
start_of_output = len(inputs.input_ids[0])

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

outputs = model.generate(
        inputs.input_ids.to(device),
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.eos_token_id,
        do_sample=True,
        temperature=0.3,
        max_new_tokens=100,
        )

output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True)  

Model Card Contact

Darren Oberst & llmware team