|
--- |
|
title: NLP_project |
|
emoji: 💣 |
|
colorFrom: indigo |
|
colorTo: pink |
|
sdk: streamlit |
|
sdk_version: 1.31.0 |
|
app_file: app.py |
|
pinned: false |
|
--- |
|
|
|
# Streamlit app with neural network 💡 |
|
|
|
## Team🧑🏻💻 |
|
1. [Diachenko Ilia](https://github.com/DiaElijah) |
|
2. [Nikita Yakubovskiy](https://github.com/Yani464) |
|
|
|
## Task 📌 |
|
1. Create a service for classifying user-entered reviews of a medical institution using classical ML models and neural networks. |
|
2. Create a service for assessing the degree of taxiness of user-entered text using the BERT model. |
|
3. Horoscope generation using neural networks. |
|
|
|
## Contents 🤖 |
|
1. For classifying user-entered reviews of a medical institution used 👾 [bert-base-cased](https://huggingface.co/Geotrend/bert-base-ru-cased) |
|
2. Text toxicity meter 🦠 [rubert-tiny-toxicity](https://huggingface.co/cointegrated/rubert-tiny-toxicity) |
|
3. Horoscope engine is 👽 [GPT2](https://colab.research.google.com/drive/1sD_hQJOi3CrHn7Ba-XuKkHRToxDRRSof?usp=sharing#scrollTo=D5Eezvzm_hrI) |
|
|
|
## Libraries 📖 |
|
```python |
|
import streamlit as st |
|
import numpy as np |
|
import pandas as pd |
|
import time |
|
import torch |
|
import torch.nn as nn |
|
from torch import tensor |
|
|
|
import joblib |
|
from dataclasses import dataclass |
|
from transformers import AutoTokenizer, AutoModel, AutoModelForSequenceClassification, GPT2LMHeadModel, GPT2Tokenizer |
|
import json |
|
``` |
|
|
