Evaluate1.py

from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer, AutoConfig, AutoModel
from datasets import Dataset, DatasetDict, Features, Sequence, ClassLabel, Value
import pandas as pd
import re
import torch
from Preprocess import *

model_path = "Model-V1.1"
tokenizer = AutoTokenizer.from_pretrained(model_path)
config = AutoConfig.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path, config=config)
labels = model.config.id2label
label2id = model.config.label2id

def preprocess(code):
    # code = format_cpp(code)
    code = remove_comments(code)
    code = replace_preprocessor(code)
    code = normalize_braces(code)
    code = strip_lines(code)
    return code


def eval(source):
    source = preprocess(source)
    inputs = tokenizer(
        source,
        truncation=True,
        padding='max_length',
        max_length=512,
        return_tensors='pt'
    )

    model.cpu()
    model.eval()
    inputs = {k: v.cpu() for k, v in inputs.items()}

    with torch.no_grad():
        outputs = model(**inputs)

    probs = torch.softmax(outputs.logits, dim=-1).detach().cpu().numpy()[0]
    pred_id = probs.argmax()
    # print("Label:", labels[pred_id], " | Score:", probs[pred_id])
    return labels[pred_id], f"{probs[label2id['AI']]*100:.2f} %"