This project is a Streamlit app that uses the mGPT-XL (1.3B) model to generate Azerbaijani text. Users can input partial text, and the model will complete it with contextually relevant text in Azerbaijani.
To run the Streamlit app locally, you need to set up a Python environment and install the required dependencies. Follow these steps:
-
Clone the repository to your local machine:
git clone https://github.com/NijatZeynalov/mgpt-az-streamlit.git cd mgpt-az-streamlit -
Install the project dependencies:
pip install -r requirements.txt
Once you have set up the environment, you can run the Streamlit app:
streamlit run main.pyThe app will be accessible in your web browser at http://localhost:8501. You can enter partial text in the provided input field and click the "Tamamla" (Complete) button to generate text.
This project includes a Dockerfile for containerizing the Streamlit app. Follow these steps to build and run the Docker container:
- Build the Docker image:
docker build --no-cache -t streamlit-az-text .- Run the Docker container (mapping port 8501 to the host):
docker run -p 8501:8501 streamlit-az-textYou can see a demo of how the app works below:
This project is licensed under the MIT License. See the LICENSE file for details.
I've utilized the impressive mGPT-1.3B model, which is available through the Hugging Face model hub.
- Model: mGPT-1.3B for Azerbaijani
Using open-source models not only accelerates innovation but also fosters collaboration within the AI community. I am grateful for the contributions of the Hugging Face community and the accessibility of this model, which has enriched the project.
Feel free to explore the model's capabilities and contribute to its ongoing development!