A targeted resource for mastering Hugging Face libraries in Python, featuring practice problems, code examples, and interview-focused NLP concepts. Covers model fine-tuning, tokenization, and deployment for excelling in AI and data science interviews.

This is a collection of Machine Learning notebooks, datasets and more.

Fine-tune YOLOv9 for custom object detection with this step-by-step guide, including dataset preparation, training, validation, and inference tools.

A structured DreamBooth fine-tuning framework for Stable Diffusion, enabling reproducible experiments on model personalization through controlled preprocessing, training schedules, and configuration management.

A local Retrieval-Augmented Generation (RAG) agent that answers natural language questions from CSV files using a fine-tuned BERT model. Built with Streamlit UI, full training pipeline, and optional FAISS support for vector search.

Text Summarizer Flask Application is a web app that uses a BART-based model to summarize user-provided text. It stores inputs and summaries in a SQLite database and includes functionality to fine-tune the model with stored data.

Shakespearify: A Modern English to Shakespearean Translator

Identify algorithmic structures in source code using Abstract Syntax Trees (ASTs) and a CodeBERTa-based classifier. Combines syntactic analysis with transformer embeddings for structure classification from small datasets.

Predicting obesity levels using eating habits and physical condition data with machine learning and data analysis techniques.

A transfer learning project using MobileNet and the Alpaca Dataset for image classification. Includes data preprocessing, model fine-tuning, evaluation, and deployment. Demonstrates efficient computer vision workflows with small, specialised datasets.

A **real** transformer model fine-tuned using LoRA (Low-Rank Adaptation) that embodies Minnesota Nice culture with excessive politeness, apologizing for everything, and liberal use of "ope," "don'tcha know," and "you betcha."

🪘 Tabla Drum Image Generator – AI-powered tabla drum image generation using Stable Diffusion & GANs. Features custom dataset curation, ML training pipeline, and scalable API deployment.

A machine learning project that classifies news articles as Fake or True using TF-IDF vectorization and a Random Forest classifier. It provides a credibility score and supports user feedback–based retraining to improve prediction accuracy over time.

Torch and Transformers Playground: Learn and Code Deep Learning using PyTorch and HuggingFace Transformers.

L'objectif de ce challenge est de proposer une méthode de classification, basée sur des réseaux de neurones, permettant de classer des images issues de Google Quickdraw (https://quickdraw.withgoogle.com/data). Le jeu de données proposé comprend 5 classes balancées, avec 15000 exemples d'apprentissage et 5000 exemples de validation.

GatorSched harnesses GPT-2 to intelligently parse and respond to queries from lifelog data, providing tailored recommendations and insights for effective scheduling

Powerful Python tool for visualizing and interacting with pre-trained Masked Language Models (MLMs) like BERT. Features include self-attention visualization, masked token prediction, model fine-tuning, embedding analysis with PCA/t-SNE, and SHAP-based model interpretability.

A collection of AI project related to Transformer, LLM (BERT, LLAMA 2, GPT), Natural Language Processing, Model Finetuning, NER, LoRA, LangChain, RAG, Model Evaluation, HuggingFace, AWS Bedrock, Azure AI