pvduy's picture
Create README.md
e8d7ed6

How to use

from transformers import AutoModelForSequenceClassification, AutoTokenizer

ckpt = "pvduy/rm_stablebeluga_13b_arena_synth"
model = AutoModelForSequenceClassification.from_pretrained(ckpt)
tokenizer = AutoTokenizer.from_pretrained(ckpt)
rm_score = model(**tokenizer("USER: Hello! ASSISTANT: This sentence is a lie.</s>", return_tensors="pt"))[0].item()