Skip to content

Latest commit

 

History

History
53 lines (37 loc) · 2.09 KB

README.md

File metadata and controls

53 lines (37 loc) · 2.09 KB
Raw

Microsoft-Phi-2-Streamlit

Microsoft Phi 2 Streamlit App, deployed on HuggingFace Spaces is based on the Microsoft Phi 2 small language model (SLM) for text generation. Utilizing Streamlit, this application enables users to effortlessly engage with Phi 2, generating text that is contextually rich in response to their prompts.

Temperature - 0.9, max_new_tokens = 512
  • It is a bit irrelevant in the output as temperature (parameter for creativity of prompt output). Image
Temperature - 0.1, max_new_tokens = 512

  • Correct output but some unwanted tokens leakage in the prompt output. Image

    Getting Started

  1. Clone the Repository:

    git clone https://github.com/your-username/Microsoft-Phi-2-Streamlit.git
cd Microsoft-Phi-2-Streamlit

  2. Install Dependencies:

    pip install -r requirements.txt

  3. Run the App:

    streamlit run app.py

    This command will launch the app in your default web browser.

Usage

  1. Enter your text prompt in the provided text area.
  2. Click the "Generate" button to initiate text generation based on your prompt.
  3. Explore the generated output provided by the Microsoft Phi 2 language model.

Acknowledgments

  • Microsoft Phi 2 language model - Microsoft Research team in advancing language model capabilities.
  • Streamlit development group.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Issues and Contributions

If you encounter any issues or have suggestions for improvements, please feel free to open an issue or submit a pull request. Your contributions are highly valued!

Enjoy generating text with Microsoft Phi 2!