Chattobotto is your go-to medical assistance chatbot, designed to provide accurate and instant information about medical queries. Powered by the advanced ChatGPT model, it's equipped with 7 million parameters and has been fine-tuned using a supervised approach. With a primary focus on medical chat datasets and small talk datasets, Chattobotto is finely tuned to cater to your medical informational needs.

Welcome to My Awesome Project! This project uses the amazing Hugging Face library.

Check out the Hugging Face code for the ChatBot for more information.

• Supervised Fine-Tuning: We've harnessed the power of supervised fine-tuning to train Chattobotto. This process has honed its responses to ensure accurate and reliable medical information.

• LLaMa 2 Architecture: The underlying architecture of Chattobotto is based on Llama 2, providing a robust and efficient foundation for its performance.

• BPE Encoder: Chattobotto utilizes an Byte-Pair Encoder as a tokenizing algorithm, streamlining the input processing and generating meaningful responses.

• 7 Billion Parameters: With a staggering 7 million parameters, Chattobotto has been fine-tuned to excel in comprehending and generating human-like text.

• Medical and Small Talk Datasets: We've meticulously trained Chattobotto using diverse medical chat datasets and small talk datasets. This comprehensive training ensures it can handle a wide array of medical queries and engage in friendly casual conversations.

• HTML/CSS: Chattobotto boasts a sleek and intuitive user interface crafted using HTML and CSS.

• JavaScript: The interactive elements and dynamic features of the chatbot interface are implemented using JavaScript.

• Flask: Chattobotto employs Flask, a lightweight web application framework, to seamlessly manage the backend interactions between the user interface and the ChatGPT model.

• AWS (Amazon Web Services): Our deployment is powered by AWS, ensuring scalability, availability, and reliability in serving users.

To start interacting with Chattobotto, follow these simple steps:

1. Clone the Repository: Clone this repository to your local machine.

2. Install Dependencies: Navigate to the project directory and install the necessary dependencies using your preferred package manager, such as pip.

3. AWS Setup: Set up an AWS account and configure services for hosting and deployment, following AWS documentation.

4. Launch the Application: Launch the Flask application by running the appropriate command. This initiates the local server and allows you to access Chattobotto via your web browser.

5. Engage with Chattobotto: Once the application is up, start a conversation with Chattobotto. Ask medical questions or engage in small talk – it's here to assist and chat!

6. load the model from hugging face hub to fine tune it more on your specific medical assistance and research purpose

Chattobotto's knowledge foundation is built on a meticulously curated medical chat dataset and a small talk dataset. We've employed supervised fine-tuning to enhance its medical expertise, resulting in a chatbot that provides reliable medical insights.

We encourage contributions to further enrich Chattobotto's capabilities. Whether it's refining its medical responses or enhancing its usability, your contributions are welcome through pull requests.

For feedback or issues, please open a ticket in the repository. Your insights play a pivotal role in making Chattobotto even better.