This project utilizes a fine-tuned Large Language Model (LLM) to generate train scheduling information from unstructured textual data, providing an interactive UI via Streamlit.
Below is a short demo of the project in action:
git clone https://github.com/fshnkarimi/train_scheduling_assistant.git
cd train_scheduling_assistant
pip install -r requirements.txt
Run the Streamlit app locally:
streamlit run app.py
Navigate to http://localhost:8501
in your web browser to interact with the application.
llm/
: Contains files related to the fine-tuning and usage of the LLM.data/
: Store your synthetic and real-world data for training and evaluation.nlp/
: Contains Natural Language Processing utilities for text preprocessing and information extraction.models/
: Place to store the fine-tuned LLM model.app.py
: Streamlit application for user interaction and visualization.requirements.txt
: List of Python dependencies required for the project.
- Python
- PyTorch
- Hugging Face Transformers
- Streamlit
- Docker
- Kubernetes