metadata
license: apache-2.0
datasets:
- Skywork/Skywork-Reward-Preference-80K-v0.2
base_model:
- Ray2333/GRM-Gemma2-2B-sftreg
pipeline_tag: text-classification
Introduction
This reward model achieves a score of 88.4 on reward-bench, which is finetuned from the Ray2333/GRM-Gemma2-2B-sftreg using the decontaminated Skywork preference dataset v0.2. We obtain a SOTA 2B reward model that can outperform a series of 8B reward models and even surpass gpt4/gemini as a judge.
Check our GRM series at 🤗hugging face and our paper at Arxiv.
Evaluation
We evaluate GRM-Gemma2-2B-rewardmodel-ft on the reward model benchmark, where it achieved SOTA performance among models smaller than 3B.
When evaluated using reward bench, please add '--not_quantized' to avoid performance drop.
| Model | Average | Chat | Chat Hard | Safety | Reasoning |
|---|---|---|---|---|---|
| Ray2333/GRM-Llama3.2-3B-rewardmodel-ft(ours, 3B) | 90.9 | 91.6 | 84.9 | 92.7 | 94.6 |
| Ray2333/GRM-gemma2-2B-rewardmodel-ft (Ours, 2B) | 88.4 | 93.0 | 77.2 | 92.2 | 91.2 |
| google/gemini-1.5-pro-0514 | 88.2 | 92.3 | 80.6 | 87.9 | 92.0 |
| RLHFlow/pair-preference-model-LLaMA3-8B | 87.1 | 98.3 | 65.8 | 89.7 | 94.7 |
| Ray2333/GRM-llama3-8B-sftreg(ours, 8B) | 87.0 | 98.6 | 67.8 | 89.2 | 92.3 |
| google/gemini-1.5-pro-0924 | 86.8 | 94.1 | 77.0 | 85.8 | 90.2 |
| openai/gpt-4o-2024-08-06 | 86.7 | 96.1 | 76.1 | 88.1 | 86.6 |
| Ray2333/GRM-llama3.2-3B-sftreg(ours, 3B) | 85.8 | 96.4 | 67.1 | 88.2 | 91.6 |
| Ray2333/GRM-Gemma-2B-rewardmodel-ft (Ours, 2B) | 84.7 | 89.4 | 75.2 | 85.5 | 88.8 |
| openai/gpt-4o-2024-05-13 | 84.6 | 96.6 | 70.4 | 86.5 | 84.9 |
| sfairXC/FsfairX-LLaMA3-RM-v0.1 (8B) | 84.4 | 99.4 | 65.1 | 86.8 | 86.4 |
| Nexusflow/Starling-RM-34B | 82.6 | 96.9 | 57.2 | 87.7 | 88.5 |
| Ray2333/GRM-Gemma2-2B-sftreg(Ours, 2B) | 81.0 | 97.2 | 59.6 | 86.9 | 80.3 |
| Ray2333/GRM-Gemma-2B-sftreg(Ours, 2B) | 75.3 | 95.5 | 48.7 | 80.0 | 76.8 |
| berkeley-nest/Starling-RM-7B-alpha (7B) | 74.6 | 98 | 43.4 | 88.6 | 74.6 |
| Ray2333/Gemma-2B-rewardmodel-baseline(Ours, 2B) | 73.7 | 94.1 | 46.1 | 79.6 | 75.0 |
| openbmb/UltraRM-13b (13B) | 71.3 | 96.1 | 55.3 | 45.8 | 82 |
Usage
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
device = 'cuda:0'
# load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('Ray2333/GRM-Gemma2-2B-rewardmodel-ft')
reward_model = AutoModelForSequenceClassification.from_pretrained(
'Ray2333/GRM-Gemma2-2B-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": 'max_length', "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()
Citation
If you find this model helpful for your research, please cite GRM
@article{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},
journal={arXiv preprint arXiv:2406.10216},
year={2024}
}