How to use edbeeching/gpt2_reward_model with Transformers:
# 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")
SFconvertbot