README.md

metadata

title: AI Based Data Cleaner
emoji: 🚀
colorFrom: red
colorTo: red
sdk: streamlit
app_file: src/streamlit_app.py
app_port: 8501
tags:
  - streamlit
pinned: false
short_description: Comprehensive AI-powered data cleaning and validation web ap
license: mit
sdk_version: 1.46.1

🤗 Hugging Face

Hugging Face is the AI community building the future. Our platform provides tools, libraries, and resources to discover, collaborate on, and build with state-of-the-art machine learning models.

🚀 Features

📚 Model Hub

• Access thousands of pre-trained models for NLP, computer vision, audio, and more
• Filter models by task, framework, language, and license
• Community-contributed models with documentation and examples

🧠 Transformers Library

• Easy-to-use API for state-of-the-art models (BERT, GPT, T5, LLaMA, etc.)
• Multi-framework support (PyTorch, TensorFlow, JAX)
• Optimized for research and production

🔍 Datasets

• Thousands of ready-to-use datasets for various ML tasks
• Standardized access pattern across all datasets
• Efficient data loading and preprocessing

🛠️ Spaces

• Interactive ML demos and applications
• Share your models with the community
• Built-in deployment and hosting

📋 Installation

Basic Installation

pip install transformers

With TensorFlow

pip install 'transformers[tf-cpu]'

With Flax

pip install 'transformers[flax]'

For Apple Silicon (M1/ARM)

# Install prerequisites
brew install cmake
brew install pkg-config

# Then install TensorFlow
pip install 'transformers[tf-cpu]'

🚀 Quick Start

Verify Installation

from transformers import pipeline
print(pipeline('sentiment-analysis')('we love you'))
# Output: [{'label': 'POSITIVE', 'score': 0.9998704791069031}]

🔥 Popular Models

LLaMA & LLaVA Models

• LLaMA: High-performance foundation models
• LLaVA-NeXT: Improved reasoning, OCR, and world knowledge
• VipLLaVA: Understanding arbitrary visual prompts

Multimodal Models

• CLIP: Connect images and text
• Stable Diffusion: Generate images from text
• Whisper: Speech recognition and translation

🧪 MLX Support

• Native support for Apple silicon
• Efficient model training and serving
• Examples for text generation, fine-tuning, image generation, and speech recognition

📊 Example Use Cases

Text Classification

from transformers import pipeline
classifier = pipeline("sentiment-analysis")
result = classifier("I love working with Hugging Face!")
print(result)

Image Analysis

from transformers import pipeline
image_classifier = pipeline("image-classification")
result = image_classifier("path/to/image.jpg")
print(result)

Multimodal Analysis

# Analyzing artistic styles with multimodal embeddings
import fiftyone as fo
import fiftyone.utils.huggingface as fouh

dataset = fouh.load_from_hub(
    "huggan/wikiart",
    format="parquet",
    classification_fields=["artist", "style", "genre"],
    max_samples=1000,
    name="wikiart",
)

📖 Documentation

Visit huggingface.co/docs for comprehensive documentation.

🤝 Contributing

Join the Hugging Face community to collaborate on models, datasets, and Spaces.

📄 License

This project is licensed under the Apache 2.0 License - see the LICENSE file for details.

---

Made with ❤️ by the Hugging Face team and community