README.md

metadata

title: Phi 2 Fine Tuned Chatbot
emoji: 🌍
colorFrom: purple
colorTo: pink
sdk: gradio
sdk_version: 5.22.0
app_file: app.py
pinned: false
short_description: Phi-2 Conversational Assistant

Phi-2 Conversational Assistant

A fine-tuned version of Microsoft's Phi-2 model for conversational AI, deployed using Gradio interface.

Features

• Built on Microsoft's Phi-2 language model
• Fine-tuned for conversational tasks
• Interactive web interface using Gradio
• CPU-based inference for accessibility
• Configurable response parameters
• Context-aware conversations

Installation

1. Clone the repository
2. Install dependencies:

pip install -r requirements.txt

Usage

Run the application:

python app.py

The application will launch a local web server. You can interact with the chatbot through the Gradio interface.

Model Configuration

The chatbot uses the following settings:

• Maximum new tokens: 96
• Temperature: 0.6
• Top-p sampling: 0.7
• No repeat ngram size: 3
• Repetition penalty: 1.2

Project Structure

.
├── app.py                  # Main application file
├── requirements.txt        # Project dependencies
└── phi2-finetuned-final/  # Fine-tuned model files
    ├── adapter_config.json
    ├── adapter_model.safetensors
    └── tokenizer files