import streamlit as st from datasets import load_dataset from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModel, Trainer, TrainingArguments, LineByLineTextDataset import json @st.cache() def get_model(): model = AutoModelForSequenceClassification.from_pretrained("siebert/sentiment-roberta-large-english", num_labels=2) model.load_state_dict(torch.load('model')) return model @st.cache() def get_tokenizer(): tokenizer = AutoTokenizer.from_pretrained("siebert/sentiment-roberta-large-english") return tokenizer def make_prediction(): model = get_model() tokenizer = tokenizer() st.header("Sentiment analysis on twitter datasets") st.markdown("Here is a sentiment model further trained on a slice of a twitter dataset") st.markdown(""" """, unsafe_allow_html=True) text = st.text_area("Try typing something here! \n You will see how much better our model is compared to the base model! No kidding") # ^-- показать текстовое поле. В поле text лежит строка, которая находится там в данный момент ### Loading and tokenizing data # data = load_dataset("carblacac/twitter-sentiment-analysis") # tokenizer = AutoTokenizer.from_pretrained("siebert/sentiment-roberta-large-english") # dataset = data.map(lambda xs: tokenizer(xs["text"], truncation=True, padding='max_length')) # dataset = dataset.rename_column("feeling", "labels") with st.form(key='input_form'): to_analyze = st.text_input(label='Input text to be analyzed') button = st.form_submit_button(label='Classify') if button: if to_analyze: make_prediction(to_analyze) else: st.markdown("Empty request. Please resubmit") # classifier = pipeline('sentiment-analysis', model="distilbert-base-uncased-finetuned-sst-2-english") # raw_predictions = classifier(text) # тут уже знакомый вам код с huggingface.transformers -- его можно заменить на что угодно от fairseq до catboost # st.markdown(f"{raw_predictions}") # выводим результаты модели в текстовое поле, на потеху пользователю