license: apache-2.0
Model Card for Model ID
BLING-1.4b-0.1 is the first model release in the BLING ("Best Little Instruction-following No-GPU-required") model series, designed as custom instruct-following laptop-effective GPT decoder-based models (~1B-2.7B parameters).
BLING models are fine-tuned with distilled high-quality custom instruct datasets, targeted at a specific subset of instruct tasks with the objective of providing a high-quality Instruct model that can be run entirely without a GPU server, with good quality instruct-following capability that can be loaded and run locally on a laptop even without using any quantization optimizations.
Model Description
- Developed by: llmware
- Model type: GPTNeoX instruct-trained decoder
- Language(s) (NLP): English
- License: Apache 2.0
- Finetuned from model [optional]: EleutherAI/Pythia-1b-deduped
Uses
The intended use of BLING models is two-fold:
Provide a high-quality Instruct models that can run on a laptop for local testing. We have found it extremely useful when building a proof-of-concept, or working with sensitive enterprise data that must be closely guarded, especially in RAG use cases.
Push the state of the art for smaller Instruct-following models in the 1B - 7B range through improved fine-tuning datasets and targeted "instruction" tasks.
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. Rather than try to be "all things to all people," BLING models try to focus on a narrower set of Instructions more suitable to a ~1B parameter GPT model.
BLING is ideal for rapid prototyping, testing, and the ability to perform an end-to-end workflow locally on a laptop without having to send sensitive information over an Internet-based API.
The first BLING models have been trained on question-answering, key-value extraction, and basic summarization as the core instruction types.
Out-of-Scope Use
BLING is not designed for 'chat-bot' or 'consumer-oriented' applications.
BLING is not optimal for most production applications, other than simple and highly specific use cases.
Bias, Risks, and Limitations
BLING has not been designed for end consumer-oriented applications, and there has not been any focus in training on safeguards to mitigate potential bias. We would strongly discourage any use of BLING for any 'chatbot' use case.
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("llmware/bling-1.4b-0.1")
model = AutoModelForCausalLM.from_pretrained("llmware/bling-1.4b-0.1")
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}}
Citation [optional]
BLING models are built on top of EleutherAI/Pythia base - please see citation for Pythia below:
@misc{biderman2023pythia, title={Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling}, author={Stella Biderman and Hailey Schoelkopf and Quentin Anthony and Herbie Bradley and Kyle O'Brien and Eric Hallahan and Mohammad Aflah Khan and Shivanshu Purohit and USVSN Sai Prashanth and Edward Raff and Aviya Skowron and Lintang Sutawika and Oskar van der Wal}, year={2023}, eprint={2304.01373}, archivePrefix={arXiv}, primaryClass={cs.CL} }
Model Card Contact
Darren Oberst & llmware team
Please reach out anytime if you are interested in this project and would like to participate and work with us!