metadata
license: apache-2.0
datasets:
- argilla/ultrafeedback-binarized-preferences-cleaned
language:
- en
base_model:
- meta-llama/Llama-2-7b-hf
pipeline_tag: text-classification
This is the base reward model ("LLaMA-2 RM") used in the paper "DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging".
The detailed training/evaluation information can be found at https://api.wandb.ai/links/merge_exp/g56s1tul.
For the detailed information about this model, please refer to our paper.
If you found this model useful, please cite our paper:
@article{lin2024dogerm,
title={DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging},
author={Lin, Tzu-Han and Li, Chen-An and Lee, Hung-yi and Chen, Yun-Nung},
journal={arXiv preprint arXiv:2407.01470},
year={2024}
}