README.md

---
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.

```python
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)
```