Model Card for Model ID

Gemma-3-1B Astro-MCQA

Fine-tuned Gemma-3-1B on the Astro-MCQA dataset for astronomy multiple-choice question answering.

Model Description

  • Developed by: Vishwani Bhagya Geeganage

Task

  • Multiple-choice question answering (MCQA)
  • Astronomy domain

Training

  • Base model: google/gemma-3-1b-it
  • Fine-tuning: Supervised fine-tuning
  • Epochs: 3
  • Optimizer: AdamW
  • Precision: FP16

Inference

Use option scoring instead of free-text generation for best accuracy.

Downloads last month
4
Safetensors
Model size
1.0B params
Tensor type
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support