|
--- |
|
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](https://huggingface.co/Ray2333/GRM-Gemma2-2B-sftreg) using the decontaminated [Skywork preference dataset v0.2](https://huggingface.co/datasets/Skywork/Skywork-Reward-Preference-80K-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](https://huggingface.co/collections/Ray2333/grm-66882bdf7152951779506c7b), our paper at [Arxiv](https://arxiv.org/abs/2406.10216), and github repo at [Github](https://github.com/YangRui2015/Generalizable-Reward-Model). |
|
|
|
|
|
|
|
## Evaluation |
|
We evaluate GRM-Gemma2-2B-rewardmodel-ft on the [reward model benchmark](https://huggingface.co/spaces/allenai/reward-bench), 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](https://huggingface.co/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](https://huggingface.co/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](https://huggingface.co/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](https://huggingface.co/Ray2333/GRM-llama3.2-3B-sftreg)**(ours, 3B)**|85.8|96.4|67.1|88.2|91.6| |
|
|[Ray2333/GRM-Gemma-2B-rewardmodel-ft](https://huggingface.co/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](https://huggingface.co/Ray2333/GRM-Gemma2-2B-sftreg)**(Ours, 2B)** | 81.0 | 97.2 | 59.6 | 86.9 | 80.3 | |
|
| [Ray2333/GRM-Gemma-2B-sftreg](https://huggingface.co/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](https://huggingface.co/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 |
|
``` |
|
@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} |
|
} |
|
``` |
