Ray2333/Gemma-2B-rewardmodel-baseline

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# cargar modelo y tokenizador
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)
# se verá así: " 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? \n 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? \n".

kwargs = {"padding": 'max_length', "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()