Rag (Retreival Augmented Generation) Python solution with LLama3, LangChain, Ollama and ChromaDB in a Flask API based solution

Use your open source local model from the terminal

Create a chatbot in less than 2 minutes with MLX Server, Chainlit and Llama3

Terminal based LLM UI allowing multi-LLMs in chat and saving/loading (plus a streamlit version)

LLaMA3-Quantization

CodeAggregatorAI is a powerful Groq, Llama3 and Streamlit application designed to aggregate an entire GitHub repository into a single, organized Markdown file, making it easy to feed to AI systems for tasks like code summarization, question answering, code generation and fine-tuning. 🧠

⚡Powered by Groq LPUs and the latest (July 2024) Llama 3 Models to generate high-quality engineered prompts and datasets for fine-tuning AI models. Try this free Streamlit application designed to help you become a prompt engineering and fine-tuning pro.

My first open source LLM API deployment - BritneyBot!

Finetuning LLaMA 3.2-1B-Instruct model using qLoRA and LoRA quantization PEFT methods

Text handling with LLMs

GenAI based search engine

This is a Python simple game developed using Pygame, where the red square (controlled by an AI) tries to escape from the black square (controlled by the player). The AI believes the player is an enemy and uses four commands - left, right, up, down - to flee from it.