Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset

Small finetuned LLMs for a diverse set of useful tasks

Querypls🛠️: WebApp that Simplify SQL with Your Prompts. Transforming questions into SQL commands effortlessly.

Code and resources showcasing the Retrieval-Augmented Generation (RAG) technique, a solution for enhancing data freshness in Large Language Models (LLMs). Incorporate up-to-date external knowledge into LLM-generated responses. Additionally, this repository includes a Gradio-based user interface for seamless model deployment.

Simply input any YouTube video URL, and watch in awe as AI analyzes the content and provides answers to your questions in real-time. 🤯 Study smarter, save time, and unlock a whole new level of video interaction!

Solving the Enem exam with LLMs

An AI-app that allows you to upload a PDF and ask questions about it. It uses OpenAI's LLMs to generate a response.

This Midjourney prompt generator makes digital creators life easier by generating some specific prompts for Midjourney which enables them to generate more accurate and realistic images as per their needs.

An algorithmic trading system based on FinGPT, demonstrating new applications of large pre-trained Language Models in quantitative finance.

"Chatea con PDF" es una aplicación de chat que utiliza el potente modelo de lenguaje Falcon 7B con licencia Apache 2 para interactuar con archivos PDF. Dame uns estrella y sigueme.

This is course project for DSCI 6004 deals with fine-tuning a pretrained model llm with a custom data

Code submission for the "Specializing Large Language Models for Telecom Networks by ITU AI/ML in 5G" challenge

This repository contains code for setting up a conversational AI chatbot using the Falcon-7B-Instruct model and Gradio for the user interface.

Venture AI, your automated travel agent!

Comfy is a Discord-bot powerd by Falcon-7b, finetuned with the counsel-chat dataset using the Lit-GPT library

Streamlit chatbot app that can answer questions based on a pdf. see the readme for more information

This project involves fine-tuning the Falcon 7B language model to generate detailed and creative descriptive prompts. Leveraging the power of Low-Rank Adaptation (LoRA) and quantization techniques, the fine-tuning process optimizes the model for efficiency and performance.

A cybersecurity chatbot developed by fine-tuning Falcon-7B and Llama-2-7B using QLoRA on a custom question-answer dataset, which was compiled from the OWASP Top 10 and CVE vulnerability information.