Chitrarth

🚀 Chitrarth: Bridging Vision and Language for a Billion People

Chitrarth integrates a state - of - the - art multilingual LLM with a vision module, enabling image - text processing across 10 Indian languages and English, aiming to serve a vast population.

🚀 Quick Start

To quickly get started with Chitrarth, you can access the model via the web interface at Chitrarth Online. For local inference, follow the steps in the "Inference code" section.

✨ Features

• Multilingual Support: Supports 10 Indic languages (Hindi, Bengali, Telugu, Tamil, Marathi, Gujarati, Kannada, Malayalam, Odia, and Assamese) along with English.
• Model Architecture: Utilizes Krutrim - 1 as the base LLM and SigLIP as the visual encoder with a 2 - layer MLP.
• General - Purpose Usage: A general - purpose VLM suitable for various image - text - to - text tasks.

📦 Installation

git clone https://github.com/ola-krutrim/Chitrarth.git
conda create --name chitrarth python=3.10
conda activate chitrarth

cd Chitrarth 
pip install -e .

💻 Usage Examples

Basic Usage

python chitrarth/inference.py --model-path "krutrim-ai-labs/chitrarth" --image-file "assets/govt_school.jpeg" --query "Explain the image. "

📚 Documentation

Model Summary

Evaluation Results

Chitrarth shows excellent performance against SOTA VLMs on different academic multimodal tasks. It consistently outperforms IDEFICS 2 (7B) and PALO 7B on different benchmarks while remaining competitive on TextVQA and Vizwiz.

We introduce BharatBench, a comprehensive evaluation benchmark suite for 10 under - resourced Indic languages across 3 tasks. The performance of Chitrarth on the BharatBench Evaluation framework sets a strong baseline for future research in this domain.

📄 License

This code repository and the model weights are licensed under the Krutrim Community License.

📚 Citation

@inproceedings{
  khan2024chitrarth,
  title={Chitrarth: Bridging Vision and Language for a Billion People},
  author={Shaharukh Khan, Ayush Tarun, Abhinav Ravi, Ali Faraz, Praveen Kumar Pokala, Anagha Bhangare, Raja Kolla, Chandra Khatri, Shubham Agarwal},
  booktitle={NeurIPS Multimodal Algorithmic Reasoning},
  year={2024},
}

🤝 Contact

Contributions are welcome! If you have any improvements or suggestions, feel free to submit a pull request on GitHub.

🙏 Acknowledgement

Chitrarth is built with reference to the code of the following projects: Transformers, and [LLaVA - 1.5](https://github.com/haotian - liu/LLaVA). Thanks for their awesome work!