|
--- |
|
license: apache-2.0 |
|
inference: false |
|
--- |
|
|
|
# BLING-PHI-2-GGUF |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
**bling-phi-2-gguf** is part of the BLING 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 other similar models with comparable size and performance in RAG deployments, please see: |
|
|
|
[**bling-phi-3-gguf**](https://huggingface.co/llmware/bling-phi-3-gguf) |
|
[**bling-stable-lm-3b-4e1t-v0**](https://huggingface.co/llmware/bling-stable-lm-3b-4e1t-v0) |
|
[**bling-sheared-llama-2.7b-0.1**](https://huggingface.co/llmware/bling-sheared-llama-2.7b-0.1) |
|
[**bling-red-pajamas-3b-0.1**](https://huggingface.co/llmware/bling-red-pajamas-3b-0.1) |
|
|
|
### Benchmark Tests |
|
|
|
Evaluated against the benchmark test: [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/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 |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
- **Developed by:** llmware |
|
- **Model type:** Phi-2B |
|
- **Language(s) (NLP):** English |
|
- **License:** Apache 2.0 |
|
- **Finetuned from model:** Microsoft Phi-2B-Base |
|
|
|
## 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. 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 |
|
|
|
<!-- 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. |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
To pull the model via API: |
|
|
|
from huggingface_hub import snapshot_download |
|
snapshot_download("llmware/bling-phi-2-gguf", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False) |
|
|
|
|
|
Load in your favorite GGUF inference engine, or try with llmware as follows: |
|
|
|
from llmware.models import ModelCatalog |
|
model = ModelCatalog().load_model("bling-phi-2-gguf") |
|
response = model.inference(query, add_context=text_sample) |
|
|
|
Note: please review [**config.json**](https://huggingface.co/llmware/bling-phi-2-gguf/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set. |
|
|
|
|
|
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}} |
|
|
|
|
|
## Model Card Contact |
|
|
|
Darren Oberst & llmware team |
