metadata

library_name: transformers
license: mit
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
language:
  - en

Llama-3-Base-8B-DICE-Iter1

This model was developed using Bootstrapping Language Models with DPO Implicit Rewards (DICE) at iteration 1, based on the princeton-nlp/Llama-3-Base-8B-SFT-DPO architecture as the starting point.

Links to Other Models

Model Description

Model type: An 8B parameter GPT-like model fine-tuned on synthetic datasets.
Language(s) (NLP): Primarily English
License: MIT
Fine-tuned from model: princeton-nlp/Llama-3-Base-8B-SFT-DPO

AlpacaEval Leaderboard Evaluation Results

Model	LC. Win Rate	Win Rate
Llama-3-Base-8B-SFT-DPO	18.20	15.50
Llama-3-Base-8B-DICE-Iter1	25.08	25.77
Llama-3-Base-8B-DICE-Iter2	27.55	30.99

Citation

@article{chen2024bootstrapping,
  title={Bootstrapping Language Models with DPO Implicit Rewards},
  author={Chen, Changyu and Liu, Zichen and Du, Chao and Pang, Tianyu and Liu, Qian and Sinha, Arunesh and Varakantham, Pradeep and Lin, Min},
  journal={arXiv preprint arXiv:2406.09760},
  year={2024}
}