Hugging Face's logo

glorgao
/
SelectiveDPO-Gemma2-9B-SFT-UFBinarized

Text Generation
Transformers
Safetensors
gemma2
conversational
text-generation-inference
Model card Files
xet
Community

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

For the recipe to reproduce this model, please visit our GitHub page.

Downloads last month
2
Safetensors
Model size
9B params
Tensor type
F32
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for glorgao/SelectiveDPO-Gemma2-9B-SFT-UFBinarized

Base model

google/gemma-2-9b
Finetuned
tanliboy/zephyr-gemma-2-9b-sft
Finetuned
(2)
this model

Dataset used to train glorgao/SelectiveDPO-Gemma2-9B-SFT-UFBinarized

Collection including glorgao/SelectiveDPO-Gemma2-9B-SFT-UFBinarized

Paper for glorgao/SelectiveDPO-Gemma2-9B-SFT-UFBinarized