This project presents an explainable academic prototype for the preventive detection of four indicators related to adult mental health using the National Survey on Drug Use and Health (NSDUH) 2024. The final system combines a hybrid Machine Learning and Deep Learning predictive solution, SHAP-based explainability, and a generative AI agent layer integrating structured validation, retrieval-augmented generation (RAG), LangGraph, Mistral, and guardrails. The repository includes the five main project notebooks, experimental results, final inference files, reproducibility documentation, productization components, and a local demonstration dashboa
KGSum: Automatic Classification and Profiling of Knowledge Graphs KgSum is a Python application for extracting, preparing, and classifying Knowledge Graphs (KGs). It combines Large Language Models (such as Mistral Instructor 7B with QLoRA) and traditional machine learning for effective graph classification and profiling. Getting Started Follow these steps to set up KgSum locally. Prerequisites For Local Machine Learning Backend: Miniconda (required) Python 3.12 (suggested) CUDA 12.8 (for transformer models like Mistral) NVIDIA GPU (recommended: RTX 3070 or higher) For Frontend: Node.js npm For Docker Deployment: Docker Docker Compose Installa
Incorporating question and answer pairs is crucial for creating accurate, context-aware, and user-friendly Large Language Models. FragenAntwortLLMGPU is a Python package designed for processing PDF documents and generating efficient Q&A pairs using large language models (LLMs) on CPU and GPU. This package can be used to fine-tune an LLM. It leverages various NLP libraries and the Mistral v1 LLM (https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF) to achieve this.
Incorporating question and answer pairs is crucial for creating accurate, context-aware, and user-friendly Large Language Models. FragenAntwortLLMCPU is a Python package designed for processing PDF documents and generating efficient Q&A pairs using large language models (LLMs) on CPU. This package can be used to fine-tune an LLM. It leverages various NLP libraries and the Mistral v1 LLM ( https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF ) to achieve this.
