---
library_name: transformers
datasets:
- HuggingFaceH4/ultrafeedback_binarized
base_model:
- tanliboy/zephyr-gemma-2-9b-sft
---

This model is fine-tuned from the tanliboy/zephyr-gemma-2-9b model using the SelectiveDPO algorithm on the Ultrafeedback_binarized dataset.

For the recipe to reproduce this model, please visit our  [GitHub page](https://github.com/glorgao/SelectiveDPO).