llmware/bling-sheared-llama-2.7b-0.1-GGUF

Quantized GGUF model files for bling-sheared-llama-2.7b-0.1 from llmware

Name	Quant method	Size
bling-sheared-llama-2.7b-0.1.q2_k.gguf	q2_k	1.14 GB
bling-sheared-llama-2.7b-0.1.q3_k_m.gguf	q3_k_m	1.33 GB
bling-sheared-llama-2.7b-0.1.q4_k_m.gguf	q4_k_m	1.64 GB
bling-sheared-llama-2.7b-0.1.q5_k_m.gguf	q5_k_m	1.92 GB
bling-sheared-llama-2.7b-0.1.q6_k.gguf	q6_k	2.22 GB
bling-sheared-llama-2.7b-0.1.q8_0.gguf	q8_0	2.87 GB

Original Model Card:

Model Card for Model ID

llmware/bling-sheared-llama-2.7b-0.1 is part of the BLING ("Best Little Instruction-following No-GPU-required") model series, RAG-instruct trained on top of a Sheared-LLaMA-2.7B base model.

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 is 'inference-ready' on a CPU laptop even without using any advanced quantization optimizations.

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: 90.25 correct out of 100
--Not Found Classification: 60.0%
--Boolean: 80.0%
--Math/Logic: 50.0%
--Complex Questions (1-5): 2 (Low-Medium)
--Summarization Quality (1-5): 3 (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: Instruct-trained decoder
• Language(s) (NLP): English
• License: Apache 2.0
• Finetuned from model [optional]: princeton-nlp/Sheared-LLaMA-2.7B

Uses

The intended use of BLING models is two-fold:

1. Provide 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.

2. Push the state of the art for smaller Instruct-following models in the sub-7B parameter range, especially 1B-3B, as single-purpose automation tools for specific tasks through targeted fine-tuning datasets and focused "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 ~1-3B 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 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("llmware/bling-sheared-llama-2.7b-0.1")
model = AutoModelForCausalLM.from_pretrained("llmware/bling-sheared-llama-2.7b-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:

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}}

Citation [optional]

This BLING model was built on top of a Sheared Llama model base - for more information about the Sheared Llama model, please see the paper referenced below:

@article{xia2023sheared, title={Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning}, author={Xia, Mengzhou and Gao, Tianyu, and Zeng Zhiyuan, and Chen Danqi}, year={2023} }

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!