AspireAI_v1.2

Model Card for AspireAI 7B

<!-- Provide a quick summary of what the model is/does. -->

AspireAI is specially trained to generate Multiple Choice Questions on 6 different subjects for UPSC Preliminary Exam.

Model Details

AspireAI addresses the imperative need for modernized and optimized learning experiences for UPSC aspirants preparing for the General Studie Paper – I of Preliminary exam. Recognizing the significance of MCQs, AspireAI can generate different MCQs upto the standards of UPSC questions for Aspirants to practice and learn.

Model Description

<!-- Provide a longer summary of what this model is. -->

This model is a finetuned version of Llama 3.2 1B.

• Developed by: Vaishak Bhuvan M R, Kundan Rao S and Team
• Supported by: Dept. of AIML, B.M.S. College of Engineering, Bengaluru 560 019
• Finetuned from model : Llama 3.2 1B

Model Sources

• Paper : Coming Soon
• Demo : Coming Soon

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

• AspireAI can generate 5 MCQs at once on a single topic -
• The topics on which AspireAI can generate MCQs are:-
  • History
  • Indian Polity and Governance
  • Indian Economy
  • Science and General Technology
  • Environment and Ecology
  • Indian and World Geography

Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

The model sometimes may generate wrong answers for the questions or might hallucinate to generate questions that are not related to the syllabus of the UPSC Exam

Training Details

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

The Model has been trained on custom data collected by the team on Nvidia A5000 GPU, The Dataset cannot be disclosed for a few reasons.

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

The model was trained using the Instruction Fine-tuning format specified by the Mistral AI Team.

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

More info will be provided soon !!

Results

Coming soon !!

Project contact

For more info contact - [email protected]