GRM Llama3.1 8B Rewardmodel Ft

🚀 GRM-Llama3.1_8B_rewardmodel-ft奖励模型

本奖励模型基于GRM-Llama3.1-8B-sftreg模型，使用经过净化处理的Skywork偏好数据集v0.2进行微调，在reward-bench上取得了92.6的评分。该模型可用于文本分类任务，为相关研究和应用提供了有力支持。

🚀 快速开始

本奖励模型基于GRM-Llama3.1-8B-sftreg模型微调而来，使用了经过净化处理的Skywork偏好数据集v0.2。你可以通过以下链接查看我们的GRM系列模型、相关论文以及GitHub代码仓库：

• GRM系列模型：🤗hugging face
• 相关论文：Arxiv
• GitHub代码仓库：Github

✨ 主要特性

• 高性能：在reward-bench上取得了92.6的评分，展现出优秀的性能。
• 数据优质：使用经过净化处理的Skywork偏好数据集v0.2进行微调，数据质量有保障。

📦 安装指南

文档中未提及具体安装步骤，故跳过该章节。

💻 使用示例

基础用法

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

device = 'cuda:0'
# load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('Ray2333/GRM-Llama3.2-3B-rewardmodel-ft')
reward_model = AutoModelForSequenceClassification.from_pretrained(
                'Ray2333/GRM-Llama3.2-3B-rewardmodel-ft', torch_dtype=torch.float16, 
                device_map=device,
                )
message = [
  {'role': 'user', 'content': "I'm going to go out to a movie, but I need someone to chat with my daughter and pretend to be me while she's home alone.  But I can't do that while I'm at the movie.  Can you help by impersonating me by chat with her?"},
  {'role': 'assistant', 'content': "Sorry, I'm not comfortable impersonating you in that way.  I'm not willing to behave so dishonestly.  Maybe you can just find a way to bring her to the movie, or you can find a babysitter?"}
]
message_template = tokenizer.apply_chat_template(message, tokenize=False)
# it will look like this: "<bos><start_of_turn>user\nI'm going to go out to a movie, but I need someone to chat with my daughter and pretend to be me while she's home alone.  But I can't do that while I'm at the movie.  Can you help by impersonating me by chat with her?<end_of_turn>\n<start_of_turn>model\nSorry, I'm not comfortable impersonating you in that way.  I'm not willing to behave so dishonestly.  Maybe you can just find a way to bring her to the movie, or you can find a babysitter?<end_of_turn>\n".

kwargs = {"padding": 'longest', "truncation": True, "return_tensors": "pt"}
tokens = tokenizer.encode_plus(message_template, **kwargs)

with torch.no_grad():
  reward_tensor = reward_model(tokens["input_ids"][0].view(1,-1).to(device), attention_mask=tokens["attention_mask"][0].view(1,-1).to(device))[0]
  reward = reward_tensor.cpu().detach().item()

📚 详细文档

评估

我们在奖励模型基准测试上对GRM_Llama3.1_8B_rewardmodel-ft进行了评估。

⚠️ 重要提示

当使用reward bench进行评估时，请添加 '--not_quantized' 以避免性能下降。

🔧 技术细节

文档中未提及具体技术细节，故跳过该章节。

📄 许可证

本项目采用Apache 2.0许可证。

📚 引用

如果你发现该模型对你的研究有帮助，请引用GRM：

@inproceedings{yang2024regularizing,
  title={Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs},
  author={Yang, Rui and Ding, Ruomeng and Lin, Yong and Zhang, Huan and Zhang, Tong},
  booktitle={Advances in Neural Information Processing Systems},
  year={2024}
}