mlconvexai/gemma-2-2b-it-S-Group

The example uses a small dataset of 248 question-answer pairs from S-Group. While this small dataset will likely lead to overfitting, it effectively showcases the fine-tuning process using Unsloth. This repository is intended as a demonstration of the fine-tuning method, not a production-ready solution. Use repetition_penalty and no_repeat_ngram_size in prediction. Instructions and dataset are in GitHub.

Uploaded model

• Developed by: mlconvexai
• License: Gemma
• Finetuned from model : google/gemma-2-2b-it

This gemma2 model was trained 2x faster with Unsloth and Huggingface's TRL library.