README.md

metadata

title: Phi Finetuned Chat
emoji: 🤖
colorFrom: purple
colorTo: pink
sdk: docker
sdk_version: '3.10'
app_file: app.py
pinned: false

Simple Text Generator

A minimal Flask app for text generation with your fine-tuned model.

Features

• ✅ Single page interface
• ✅ Simple prompt → output
• ✅ No complex questionnaire
• ✅ Full terminal logging
• ✅ Clean UI
• ✅ Docker ready for Hugging Face Spaces

Files

• app.py - Main Flask application (all-in-one file)
• requirements.txt - Python dependencies
• Dockerfile - Docker configuration for HF Spaces
• .dockerignore - Files to exclude from Docker build

Quick Deploy to Hugging Face Spaces

1. Create new Space at https://huggingface.co/new-space
2. Choose Docker as SDK (not Gradio or Streamlit)
3. Upload all 4 files from this folder:
   • app.py
   • requirements.txt
   • Dockerfile
   • .dockerignore
4. Wait for build to complete
5. Access your app!

Local Usage

With Python directly:

pip install -r requirements.txt
python app.py

Open http://localhost:7860

With Docker:

docker build -t simple-text-gen .
docker run -p 7860:7860 simple-text-gen

Open http://localhost:7860

Configuration

Change model in app.py:

MODEL_NAME = "KASHH-4/phi_finetuned"  # Your model

Adjust generation settings:

max_new_tokens=100  # Number of tokens to generate
do_sample=False     # Greedy decoding (faster)

Hardware Requirements

• Minimum: 2 vCPU + 18GB RAM (CPU inference, ~60s per generation)
• Recommended: T4 GPU + 16GB RAM (GPU inference, ~3-5s per generation)