metadata
license: mit
datasets:
- mlabonne/orpo-dpo-mix-40k
language:
- en
tags:
- ORPO
Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
Model trained with the innovative ORPO method, based on the robust VAGOsolutions/SauerkrautLM-Phi-3-medium.
The model was trained with the dataset: mlabonne/orpo-dpo-mix-40k, which combines diverse data sources to enhance conversational capabilities and contextual understanding.