license: cc-by-sa-4.0
Model Card for Model ID
dragon-llama-7b-0.1 part of the dRAGon ("Delivering RAG On Private Cloud") model series, RAG-instruct trained on top of a StableLM-7B base model.
DRAGON models are fine-tuned with high-quality custom instruct datasets, designed for production quality 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: 96.25 correct out of 100
--Not Found Classification: 45.0%
--Boolean: 81.25%
--Math/Logic: 57.50%
--Complex Questions (1-5): 3 (Low-Medium)
--Summarization Quality (1-5): 4 (Coherent, extractive)
--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: StableLM-7B
- Language(s) (NLP): English
- License: Apache 2.0
- Finetuned from model: StableLM-Base-Alpha-7B-v2
Uses
The intended use of DRAGON models is two-fold:
Provide high-quality RAG-Instruct models designed for fact-based, no "hallucination" question-answering in connection with an enterprise RAG workflow.
DRAGON models are fine-tuned on top of leading base foundation models, generally in the 6-7B+ range, and purposefully rolled-out across multiple base models to provide choices and "drop-in" replacements for RAG specific use cases.
DRAGON models were trained on the same principles as the BLING models, so generally, it should be easy to "upgrade" from a BLING model in testing to a DRAGON model in production.
Direct Use
DRAGON is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services, legal and regulatory industries with complex information sources.
DRAGON 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("dragon-stable-lm-7b-v1")
model = AutoModelForCausalLM.from_pretrained("dragon-stable-lm-7b-v1")
The BLING 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:
- Text Passage Context, and
- 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}}
Model Card Contact
Darren Oberst & llmware team
Please reach out anytime if you are interested in this project!