The purpose of this project is to build a library in C++ which stores list of books and movies a user has watched. The library will then be used to fine-tune an LLM recommender model to recommend customized movies or books to an end user
Table of Contents
The project will utilize C++ to build out an application for handling the creation and addition of user movie and book libraries. The data will then be stored in a SQL database to add to later or pull data from for use in fine-tunining an LLM. The libraries will then be used to fine-tune an LLM to provide movie or book recommendations tailored to users preferences.
Required Libraries/Frameworks:
C++ compiler (GNU C++17 was used for this project)
Libpqxx
Required Hardware:
NVidia GPU (once LLM has been implemented)
- Clone the Repo
git clone https://github.com/zjshermanburke/cppTorchNN- Verify functionality by running in IDE (this project was built and run in VS code on Ubuntu)
TBD still in progress
- Build Movie Library
- Build Book Library
- Build Data Loader and Saver in C++ (Using PostgreSQL)
- Build Python PostgreSQL Data Loader
- Determine which LLM recommender model to utilize
- Build dataloader based on LLM in Python
- Create Jupyter notebook to handle fine-tuning in Python
- Implment user feedback functionality for LLM
Distributed under the Unlicense license. See LICENSE.txtfor more information.
Zachary Sherman-Burke - LinkedIn - zjshermanburke@gmail.com
Project Link: https://github.com/zjshermanburke/TransferLearning_VGG19