edbeeching

/

gpt2_reward_model

like 0

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-classification", model="edbeeching/gpt2_reward_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("edbeeching/gpt2_reward_model")
model = AutoModelForSequenceClassification.from_pretrained("edbeeching/gpt2_reward_model")