---
license: apache-2.0
---
# Towards Efficient Exact Optimization of Language Model Alignment

- **model**: [exo-imdb-reward-model](https://huggingface.co/ehzoah/exo-imdb-reward-model)

  - Finetuned from model: [gpt2-large](https://huggingface.co/openai-community/gpt2-large)

- **dataset**: [imdb](https://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz) (original stanford version)

Reward model used in the imdb experiment of the ICML'24 paper [*Towards Efficient Exact Optimization of Language Model Alignment*](https://arxiv.org/pdf/2402.00856).

For details of the dataset, training and inference of this model, please refer to https://github.com/haozheji/exact-optimization/blob/main/exp/imdb_exp/README.md