Kurtis is a fine-tuning, inference and evaluation tool built for SLMs (Small Language Models), such as Huggingface's SmolLM2.

Question-Answering Model for Schizophrenia Symptoms and Their Impact on Daily Life using Mental Health Forums Data (https://arxiv.org/abs/2310.00448)

pip install gptmed

an AI powered Arabic Question Answering system built by fine tuning the AraBERT model on the Arabic SQuAD dataset. , Developed as part of the ZakyBootcamp AI track

Extracting Emotion-Cause Pairs from Conversations: A Two-Step Approach Using Emotion Classification and QA Models

Fully automated system that generates questions and answers from various input sources—including PDF, TXT, MP3, ENEX, MP4, DOCX, PNG, JPG, PPTX, EPUB, JPEG, MPEG4, URL, YouTube, Spotify, Wikipedia, or direct text input—allowing users to solve questions within an interface and then receive a detailed report of their performance

This repository implements a question-answering system using Gradio's lower-level API, featuring two input fields for context and user questions. The system utilizes the deepset/roberta-base-squad2 model and provides a user-friendly interface for model interaction.

🤖 Enhance Arabic NLP capabilities with this AI-powered question answering system, fine-tuned on the Arabic SQuAD dataset using the AraBERT model.