README.md

---
title: Gemma Fine Tuning
emoji: 🐠
colorFrom: indigo
colorTo: green
sdk: gradio
sdk_version: 5.20.1
app_file: app.py
pinned: false
hf_oauth: true
hf_oauth_scopes:
  - inference-api
---

# Gemma Fine-Tuning UI

A user-friendly web interface for fine-tuning Google's Gemma models on custom datasets.

## Features

- **Easy Dataset Upload**: Support for CSV, JSONL, and plain text formats
- **Intuitive Hyperparameter Configuration**: Adjust learning rates, batch sizes, and other parameters with visual controls
- **Real-time Training Visualization**: Monitor loss curves, evaluation metrics, and sample outputs during training
- **Flexible Model Export**: Download your fine-tuned model in PyTorch, GGUF, or Safetensors formats
- **Comprehensive Documentation**: Built-in guidance for fine-tuning process

## Getting Started

### Prerequisites

- Python 3.8 or later
- PyTorch 2.0 or later
- Hugging Face account with access to Gemma models

### Installation

1. Clone this repository:

   ```bash
   git clone https://github.com/yourusername/gemma-fine-tuning.git
   cd gemma-fine-tuning
   ```

2. Install the required packages:

   ```bash
   pip install -r requirements.txt
   ```

3. Launch the application:

   ```bash
   python app.py
   ```

4. Open your browser and navigate to `http://localhost:7860`

## Usage Guide

### 1. Dataset Preparation

Prepare your dataset in one of the supported formats:

**CSV format**: