--- library_name: transformers datasets: - HuggingFaceH4/ultrafeedback_binarized base_model: - HuggingFaceH4/mistral-7b-sft-beta --- This model is fine-tuned from the HuggingFaceH4/mistral-7b-sft-beta model using [SelectiveDPO](https://huggingface.co/papers/2502.09650) on the Ultrafeedback_binarized dataset. For the recipe to reproduce this model, please visit our [GitHub page](https://github.com/glorgao/SelectiveDPO).