cointegrated's picture
add torch as dependency
c6948e2
import pandas as pd
import streamlit as st
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
model_checkpoint = 'cointegrated/rubert-tiny-toxicity'
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
model = AutoModelForSequenceClassification.from_pretrained(model_checkpoint)
if torch.cuda.is_available():
model.cuda()
def text2toxicity(text, aggregate=True):
""" Calculate toxicity of a text (if aggregate=True) or a vector of toxicity aspects (if aggregate=False)"""
with torch.no_grad():
inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True).to(model.device)
proba = torch.sigmoid(model(**inputs).logits).cpu().numpy()
if isinstance(text, str):
proba = proba[0]
if aggregate:
return 1 - proba.T[0] * (1 - proba.T[-1])
return proba
text = st.text_area('Введите текст', value='Пороть надо таких придурков!')
proba = text2toxicity(text, aggregate=False)
s = pd.Series(
proba.tolist() + [proba[0] * (1 - proba[-1])],
index=[
'Стиль НЕтоксичный',
'Есть оскорбление',
'Есть непотребство',
'Есть угроза',
'Смысл текста неприемлемый',
'Текст - ОК'
],
name='Оценка вероятности'
)
s