| from transformers import AutoModelForSequenceClassification, AutoTokenizer | |
| import os | |
| import numpy as np | |
| tokenizer = AutoTokenizer.from_pretrained("microsoft/deberta-v3-base") | |
| model = AutoModelForSequenceClassification.from_pretrained( | |
| os.path.realpath(os.path.join(__file__, "..", "./outputs/v2-deberta-100-max-71%-sep/checkpoint-1000/")), | |
| local_files_only=True | |
| ) | |
| text_against = "ai [SEP] I think ai is a waste of time. I don't understand why everyone is so obsessed with this subject, it makes no sense?" | |
| text_for = "flowers [SEP] I think flowers are very useful and will become essential to society" | |
| text_neutral = "Ai is a tool use by researchers and scientists to approximate functions" | |
| encoded = tokenizer(text_for.lower(), max_length=100, padding="max_length", truncation=True, return_tensors="pt") | |
| def normalize(arr: np.ndarray) -> np.ndarray: | |
| min = arr.min() | |
| arr = arr - min | |
| return arr / arr.sum() | |
| output = model(**encoded) | |
| print(output.logits.detach().numpy()[0]) | |
| print(normalize(output.logits.detach().numpy()[0])) |