Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Model Card for AspireAI 7B

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

This model is a quantized version of AspireAI V0.6 in GGUF Format.

  • Developed by: Vaishak Bhuvan M R, Kundan Rao S, A Vaishnavi
  • Finetuned from model : Mistral 7B V2

Model Sources

  • Paper : Coming Soon
  • Demo : Coming Soon

Uses

  • 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

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

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

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

Metrics

More info will be provided soon !!

Results

Coming soon !!

Project contact

For more info contact - mrvbhuvan@gmail.com

Downloads last month
0
GGUF
Model size
7.24B params
Architecture
llama
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.