ChrisPuzzo commited on
Commit
62893f9
·
verified ·
1 Parent(s): dfdec1f

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.

Files changed (1) hide show
  1. README.md +7 -0
README.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - sjsq/PrivacyPolicy
5
+ language:
6
+ - en
7
+ ---