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.

Downloads last month
9
Safetensors
Model size
2.61B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for mlconvexai/gemma-2-2b-it-S-Group

Base model

google/gemma-2-2b
Finetuned
(159)
this model