metadata
library_name: transformers
tags:
- gsm8k
- dpo
datasets:
- August4293/gsm8k_preference_dataset_it_1
language:
- en
Model Overview
This model has been fine-tuned using the The Second Iteration of GSM8K Preference Dataset with the Direct Preference Optimization algorithm. The goal of this fine-tuning is to enhance the model's performance in solving arithmetic problems on the GSM8K benchmark.