4
4
Pakistan
2 years of experience
Hey! I am Amina, a web developer and designer, specialising as a full-stack developer. I have a strong foundation in WordPress and a basic knowledge of programming languages such as Python. I am passionate about technology and innovation and eager to apply my skills to real-world projects and contribute to collaborative environments. I am particularly interested in joining hackathons to challenge myself, learn from peers, and expand my professional network.
Aslan AI relapse prevention in healthcare, particularly in mental health and addiction recovery. Many individuals struggle with emotional crises and lack accessible, immediate support during these vulnerable moments. To address this, Aslan offers an innovative AI-driven solution that provides real-time emotional support, helping users navigate challenging moments and prevent relapse. Aslan engages users in conversational, nonjudgmental interactions, dynamically adjusting its responses to validate emotions, identify underlying needs, and offer personalized interventions. The system is designed to help users express their emotions freely, offering them a safe space for self-reflection and growth. Aslan helps users develop a deeper understanding of their feelings and take actionable steps toward emotional well-being. Key functionalities include journaling prompts, mindfulness exercises, and value-driven decision-making tools that empower users to cope with stress and regain control during difficult times. The AI also features an adaptive response mechanism, which determines the best approach, whether to suggest an intervention first or help the user clarify their emotions and needs. A standout feature is the rant-friendly space, where users can vent freely, with built-in flagging mechanisms to detect concerning content based on varying threat levels (white, yellow, orange, red). This ensures that users in crisis are promptly directed to appropriate resources, such as crisis hotlines or clinical professionals. The primary target audience for Aslan includes individuals in recovery from addiction, those dealing with mental health issues, and anyone who needs ongoing emotional support. By offering real-time interventions and a supportive environment, Aslan reduces the risk of relapse and creates long-term emotional resilience.
Solution Overview With the development of advanced AI models, developers, and data scientists face the challenge of efficiently evaluating and comparing multiple models for some particular tasks.LlamaEval addresses this challenge by offering a streamlined, easy-to-use evaluation dashboard for comparing Llama model outputs. By integrating the Together AI API, users can select and test multiple models. The results are displayed on an interactive dashboard with two key features: a benchmark description expander and a performance scoreboard featuring metrics. So the user has information about the benchmark used and the final evaluation scores. Tech Stack Backend: Python, Together AI, requests, pandas, nltk, scikit-learn and Hugging Face datasets Frontend: Streamlit for creating the user interface, displaying results, and providing interaction Deployment: Docker, Azure Cloud Services: Container Registry (store the docker container) and Container App (deploy and provide a url link that can be copy-pasted on the web.) Target Audience This tool is designed for data scientists, AI researchers, developers and, machine learning Engineers from enterprises, academia, and government sectors. They need efficient solutions for quick model assessment in real-world applications roughly estimating a serviceable market of ~$10B. Unique Features/Benefits • Simplicity and speed: LlamaEval offers a simple interface to quickly assess multiple models without the need for complex setups or long runtimes. • Comprehensive insights: Real-time results and detailed comparison panels. • Customizable: In the future, the users will be able to select any number of models for comparison and evaluate them on any dataset, making it versatile for a wide range of use cases.
VitalGuide is an offline emergency assistance app designed to save lives during natural disasters or situations where connectivity is unavailable. The app addresses the critical need for reliable survival guidance and emergency first-aid instructions. It uses a Retrieval-Augmented Generation (RAG) system and the Gemma 2 model to provide quick and accurate answers by leveraging government datasets and trusted sources like PDFs and guides. This is important because FEMA's manual is large and unwieldy, and slower to leaf through than our LLM tool, when the seconds matter. Gemma 2 also has general knowledge that the FEMA manual doesn't have and can be asked follow-up questions if information is unclear. Specialized for individuals, communities, and first responders, it features multilingual support, ensuring accessibility for diverse users. Its unique offline functionality guarantees availability anytime, anywhere. VitalGuide empowers users with lifesaving knowledge, bridging the gap when conventional communication methods fail.