Skip to content

Latest commit

 

History

History
36 lines (24 loc) · 1003 Bytes

README.md

File metadata and controls

36 lines (24 loc) · 1003 Bytes

Virtual Assistant for an E-commerce application

Fine tuned an open source Large language model (Llama2) using PEFT , LoRA for a chatbot application. (https://theplantera.com/ ) chatbot_gif

Installation

  1. Clone the repository:
    git clone https://github.com/enviz/theplantera-bot.git
    
  2. Create a Conda environment (recommended using Python 3.10):
    conda create --name theplantera-bot python=3.10
    
  3. Activate the Conda environment:
    conda activate theplantera-bot
    
  4. Install all the dependencies :
    pip install -r requirements.txt
    
  5. Run the streamlit app
    streamlit run app.py
    

Notebooks and Fine-Tuning

Explore the notebooks folder for data creation pipelines and fine-tuning code for the Llama2 model.

Contributing

If you wish to contribute to this project, feel free to fork the repository and submit pull requests.