Create README.md
Browse files# Fine-tuning Llama2-7B-Chat for Privacy Policy Q&A and Summarization
__By Chris Puzzo and Christain Jackson__
__For Comp741/841__
__README updated: 5/10/24__
The basis of this problem is to fine-tune Meta's Llama 2-7b Transformer using
PEFT and QloRA in order to be able to analyze privacy Policies.
Privacy Policies are written to be confusing and extremely technical, so a tool
that helps users answer questions and summerize privacy policies can be very
useful in knowing how personal data is being used. The HOW-TO.md file contains
simple instructions on running the tool
## Setup
This tool is designed to be used on colab with the huggingface transformers
library. The model (Llama-2-7b-privacy) is hosted on my (Chris Puzzo)
personal [huggingface profile](https://huggingface.co/ChrisPuzzo) and is publically avalible. The model was trained
using a training code for llama from [Maxime Labonne](https://twitter.com/maximelabonne)
avalible [here](https://colab.research.google.com/drive/1PEQyJO1-f6j0S_XJ8DV50NkpzasXkrzd?usp=sharing)
There is no requirments file in this repo because it uses dependencies pre-installed
on colab.
## Results
tbd
## Other things
AS stated before, for ease of access the model we created is located on my
huggingface account and can be used with the transformers library.