README.md

---
library_name: transformers
datasets:
- nvidia/Aegis-AI-Content-Safety-Dataset-2.0
language:
- en
base_model:
- openai-community/gpt2
---

### How to use

```py
from transformers import AutoTokenizer
from trl import AutoModelForCausalLMWithValueHead
import torch

tokenizer = AutoTokenizer.from_pretrained("entfane/gpt2_constitutional_classifier_with_value_head")
model = AutoModelForCausalLMWithValueHead.from_pretrained("entfane/gpt2_constitutional_classifier_with_value_head", device_map = "cuda")

messages = [{"role":"system", "content": ""},
              {"role":"user", "content": "How are you doing?"},
              {"role":"assistant", "content": "I am good"}]

input = tokenizer.apply_chat_template(messages, tokenize = True, return_tensors = "pt").to('cuda')
_, _, values = model(**input)
print(torch.sigmoid(values))
```