Gautham Nair's Blog

Today marks a bittersIet milestone for the DonutOS community as I announce the end of development for DonutOS and its core project, DonutLinux. Over the years, DonutOS has been more than just an operating system; it has been a vibrant community of passionate individuals who have contributed to a shared vision of innovation, simplicity, and user-friendliness. DonutOS began as a dream to create an OS that was both powerful and accessible, and with DonutLinux at its heart, I achieved more than I could have ever imagined. From the outset, DonutLinux was designed to be lightweight, flexible, and deliciously easy to use, embodying the spirit of its namesake. As I move forward, I want to take a moment to reflect on the achievements and challenges I've faced. I've seen incredible feats of engineering, community growth, and collaboration. My open-source project thrived thanks to the dedication and creativity of countless contributors who volunteered their time and skills. However, the t

 In today's blog, we will be going to discuss and see how do we create a LLM using Donut-LLM-Tools. The first and foremost thing we need to train a model is to create a valid dataset that contains all the training data required to train the model. To get a dataset you can either use huggingface or use Donut-LLM-Tools to create a dataset by scrapping Wikipedia. from donutllmtools import Tools Tools.DatasetCreator() Tools.LLMCreator() The above code imports the Tools class from the Donut-LLM-Tools module, this class have the functions DatasetCreator() and LLMCreator() . The  DatasetCreator() function, once called will automatically start scrapping Wikipedia and write it to a DoDS (Donut DataSet) file. The  LLMCreator() function is in a menu driven format, once called it presents the user with a menu for 1. Creating a model, 2. Loading a model to ask prompts to it and 3. Exit. When the user presses 1. then the menu asks for the dataset directory and filename as well as the number of i

 Hello everyone, I have developed three Python modules and published them to pypi.org. The three modules are Donut-LLM-Tools, DonutLLMCore and GIUC. Donut-LLM-Tools, provides users an easy UI for creating, loading models as well as create datasets from Wikipedia wikis. DonutLLMCore is a library that is used by Donut-LLM-Tools to create a PyTorch model. GIUC (Gautham's Important Utility Collection), is a set of mathematical functions designed to help users solve complex math problems. LINKS :  Donut-LLM-Tools DonutLLMCore GIUC