This repository contains 12+ hands-on projects built using Google Gemini Pro, Gemini Flash, and Gemini Pro 1.5 models. It covers fine-tuning, training, and deploying generative AI applications for …

RAG enhances LLMs by retrieving relevant external knowledge before generating responses, improving accuracy and reducing hallucinations.

Powerful framework for building applications with Large Language Models (LLMs), enabling seamless integration with memory, agents, and external data sources.

End-to-end fine-tuning of Hugging Face models using LoRA, QLoRA, quantization, and PEFT techniques. Optimized for low-memory with efficient model deployment

Built with Streamlit, LangChain, and Ollama. Helps with code generation, debugging, and documentation using DeepSeek models an AI programmer.

📝 DistilBERT, a lightweight Transformer model from Hugging Face, for various NLP tasks without requiring custom fine-tuning or datasets.

A chatbot powered by meta from Replicate, offering an interactive, user-friendly interface built with Streamlit for real-time AI-driven conversations.

Cohere's command-xlarge model, built with Streamlit for interactive user interface. It processes user input and generates responses in real-time.

🌙 Dark and light mode toggle feature with smooth transitions and persistent theme preferences using localStorage. Adapting to different lighting condition

💬 AI-powered assistant using OpenAI's GPT model. The project includes various components such as a web to facilitate interaction with the AI.

learn about LLMs, providing resources, examples, and hands-on exercises. Utilizing various libraries and tools to implement and experiment in real-world.

Showcases an AI assistant built with Llama, leveraging GROQ for efficient querying and processing. Create an intelligent conversational agent.

Collection of basic Natural Language Processing examples that cover essential techniques like tokenization, text representation, and text classification.

🔒 Leverages Machine Learning and Deep Learning models to identify malicious activities in network traffic, enhancing cybersecurity.

Dedicated to providing cutting-edge solutions in the field of data science, covering a range of advanced techniques like model training, evaluation etc.

📰 The Fake News Detection System uses deep learning techniques, specifically LSTM models, to classify news articles as real or fake.

💬 Classify Bengali comments as positive or negative. It provides valuable insights for social media to improve satisfaction based on sentiment analysis.

💬 It uses NLP techniques to classify reviews as positive, neutral or negative, providing valuable insights into customer feedback.

📱 Customers are likely to leave a telecom service, enabling companies to take measures for retention and create accurate churn prediction models.

📈 Implementing clustering algorithms, it provides valuable insights that can targeted marketing strategies, improve customer relationship management.

🛒 Provide a robust model that assists in flagging suspicious transactions, ultimately helping businesses improve security and reduce financial losses.

❤️ Likelihood of heart disease it analyzes user inputs such as age, gender, cholesterol levels, and other clinical features to provide accurate predictions.

🎮 Web-based game that allows users to compete against a smart AI opponent, utilizing Flask for the backend and Bootstrap for frontend.

Designed to store and retrieve high-dimensional data, such as embeddings, efficiently. It enables fast similarity searches by leveraging techniques.

✅ Spell Correction with MLOps project utilizes machine learning techniques to automatically correct spelling errors in text side by side.

🔢 C-based algorithms and exercises focused on numerical methods, such as interpolation, differentiation, and aimed for equation solving.