Inspired by Andrej Karpathy’s "Let’s Build GPT", this project guides you step‑by‑step to build a GPT from scratch, demystifying its architecture through clear, hands‑on code.

This project is an auto-filling text program implemented in Python using N-gram models. The program suggests the next word based on the input given by the user. It utilizes N-gram models, specifically Trigrams and Bigrams, to generate predictions.

Advance information retrieval system that combines advanced indexing, machine learning, and personalized search to enhance academic research and document discovery.

Solutions for Andrej Karpathy's "Neural Networks: Zero to Hero" course

Artificial Intelligence Course 4th Project: Implementing Bigram and Unigram models for filtering comments

AUT Principles and Applications of Artificial Intelligence course (Fall 2020) projects

It's a python based n-gram langauage model which calculates bigrams, probability and smooth probability (laplace) of a sentence using bi-gram and perplexity of the model.

Natural Language Processing - Part-Of-Speech Tagging

Very simple implementation of GPT architecture using PyTorch and Jupyter.

NLP-persian-poet-identification

Implementation of lightweight transformer model for character level text generation

This project is meant to generate a Local Language Model based on textual input.

Implementation of Handwritten Text Recognition Systems using TensorFlow

Detection of language of a written text using bigram letter model.

A basic application with necessary steps for filtering spam messages using bigram model with python language.

Detect the text language automatically using a bigram model, Support Vector Machines, and Artifical Neural Networks. The model is trained using the WiLI-2018 benchmark dataset, and the highest accuracy achieved on the test dataset is 99.7% with paragraph text.

👨🏻‍💻 My own repository to explore LearnQuran tech product in particular -obviously- AI stuffs

Final year major project on big data analysis of instacart dataset and finally Product Bundle Recommendation using pyspark(for clustering) and bigram for recommendation

This project leverages the NLTK library and the Reuters corpus to build a next-word prediction model using bigrams and conditional frequency distributions.