app.py

from transformers import pipeline
import torch
import torch.nn.functional as TF
import streamlit as st

model_name = "RoBERTa"

classifier = pipeline("sentiment-analysis")
defaultTxt = "I hate you cancerous insects so much"
result = classifier(defaultTxt)
st.write(result)

if (option == "RoBERTa"):
    tokenizerPath = "s-nlp/roberta_toxicity_classifier"
    modelPath = "s-nlp/roberta_toxicity_classifier"
    neutralIndex = 0
    toxicIndex = 1
elif (option == "DistilBERT"):
    tokenizerPath = "citizenlab/distilbert-base-multilingual-cased-toxicity"
    modelPath = "citizenlab/distilbert-base-multilingual-cased-toxicity"
    neutralIndex = 1
    toxicIndex = 0
elif (option == "XLM-RoBERTa"):
    tokenizerPath = "unitary/multilingual-toxic-xlm-roberta"
    modelPath = "unitary/multilingual-toxic-xlm-roberta"
    neutralIndex = 1
    toxicIndex = 0
else:
    tokenizerPath = "s-nlp/roberta_toxicity_classifier"
    modelPath = "s-nlp/roberta_toxicity_classifier"
    neutralIndex = 0
    toxicIndex = 1

tokenizer = AutoTokenizer.from_pretrained(tokenizerPath)
model = AutoModelForSequenceClassification.from_pretrained(modelPath)

tokens = tokenizer.tokenize(input_text)
token_ids = tokenizer.convert_tokens_to_ids(tokens)
input_ids = tokenizer(input_text)

batch = tokenizer(X_train, padding=True, truncation=True, max_length=512, return_tensors="pt")

with torch.no_grad():
    outputs = model(**batch)
    predictions = TF.softmax(outputs.logits, dim=1)
    labels = torch.argmax(predictions, dim=1)
    labels = [model.config.id2label[label_id] for label_id in labels.tolist()]

save_directory = "saved"
tokenizer.save_pretrained(save_directory)
model.save_pretrained(save_directory)

tokenizer = AutoTokenizer.from_pretrained(save_directory)
model = AutoModelForSequenceClassification.from_pretrained(save_directory)