metadata
base_model: meta-llama/Llama-3.1-8B
library_name: transformers
pipeline_tag: text-classification
tags:
- trl
- reward-trainer
- reward-model
- creative-writing
license: llama3.1
Llama 8B Creative Writing Verifier
This model is a LlamaForSequenceClassification reward model for scoring creative-writing stories. It should be used as a scalar verifier/reward model, not as a text-generation model.
Usage
This is a reward model, not a text-generation model. Load it with AutoModelForSequenceClassification and score the story directly as raw text. Do not apply a chat template or wrap the story in a prompt.
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model_id = "SAA-Lab/Llama8B-CreativeWritingVerifier"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSequenceClassification.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
if tokenizer.pad_token is None:
tokenizer.pad_token = tokenizer.eos_token
if model.config.pad_token_id is None:
model.config.pad_token_id = tokenizer.pad_token_id
def reward(story: str) -> float:
inputs = tokenizer(
story.strip(),
return_tensors="pt",
truncation=True,
max_length=4096,
).to(model.device)
with torch.inference_mode():
return model(**inputs).logits.squeeze(-1).float().item()
chosen_score = reward(chosen_story)
rejected_score = reward(rejected_story)
print(chosen_score > rejected_score)