llama3-1-8b-bb-rm

Quick start

reward_model = AutoModelForSequenceClassification.from_pretrained(
              reward_model_path,
              num_labels=1,
              torch_dtype=torch.bfloat16,
              attn_implementation="flash_attention_2",
              use_cache=False,
          )
inputs = xxxx (Left Padding Input Tokens)
reward = reward_model.model(*inputs).last_hidden_state
reward = reward_model.score(reward)[:, -1]

Citations

Cite OpenRLHF as:

@article{hu2024openrlhf,
  title={OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework},
  author={Jian Hu and Xibin Wu and Zilin Zhu and Xianyu and Weixun Wang and Dehao Zhang and Yu Cao},
  journal={arXiv preprint arXiv:2405.11143},
  year={2024}
}