Drawing inspiration from Andrej Karpathy’s iconic lecture, "Let’s Build GPT: From Scratch, in Code, Spelled Out", this project takes you on an immersive journey into the inner workings of GPT. Step-by-step, we’ll construct a GPT model from the ground up, demystifying its architecture and bringing its mechanics to life through hands-on coding.

Service of wrapped DeepPavlov NER ML models for a quick entities extraction from cells of long tabular data, powered by AREkit pipelines

This project demonstrates text summarization using the BART (Bidirectional and Auto-Regressive Transformers) model. BART is a transformer model trained as a denoising autoencoder and is effective for text generation tasks such as summarization.

Blip Image Captioning + GPT-2 Happy Model: Generate joyful responses to image captions using state-of-the-art NLP and computer vision. Pretrained models and data preprocessing included for seamless integration. Explore the intersection of deep learning, sentiment analysis, and language generation

Deep Learning The Foundation of AI

FluxPipeline is a prototype experimental project that provides a framework for working with the FLUX.1-schnell image generation model. This project is intended for educational and experimental purposes only.

A light implementation of the 2017 Google paper 'Attention is all you need'.

This repository employs two different architectures of Tabular Transformer models for Operating System fingerprinting from three different datasets.

A multi-label text classification model which can classify the tasks based on the abstract of publication paper.