Gemma 2B Rewardmodel Baseline

🚀 Reward Model for LLMs

This is a reward model designed for Large Language Models (LLMs). It offers a compact yet effective solution for evaluating responses, especially useful when a small - sized reward model is required.

🚀 Quick Start

This is a reward model (based on Gemma - 2b - it) trained with BT loss using the weqweasdas/preference_dataset_mixture2_and_safe_pku dataset.

This reward model is especially useful if you need a good small reward model for LLMs. You can also refer to [Ray2333/GRM - Gemma - 2B - sftreg](https://huggingface.co/Ray2333/GRM - Gemma - 2B - sftreg) for a better 2B reward model trained with a hidden states regularization.

✨ Features

• Trained on a specific dataset with BT loss, providing a reliable evaluation metric for LLMs.
• A good choice for scenarios where a small - sized reward model is needed.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('Ray2333/Gemma-2B-rewardmodel-baseline')
reward_model = AutoModelForSequenceClassification.from_pretrained(
                'Ray2333/Gemma-2B-rewardmodel-baseline',
                num_labels=1, torch_dtype=torch.float16,
                device_map=0,
                )
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 = model(tokens["input_ids"][0].to(model.device), attention_mask=tokens["attention_mask"][0].to(model.device)).logits.reshape(-1)
  reward = reward_tensor.cpu().detach().item()

📚 Documentation

Evaluation

We evaluate this reward model on the [reward model benchmark](https://huggingface.co/spaces/allenai/reward - bench).

📄 License

This project is licensed under the MIT License.