app.py

import torch
import numpy as np
import gradio as gr
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Update this to the appropriate model
tokenizer = AutoTokenizer.from_pretrained("juliensimon/autonlp-imdb-demo-hf-16622775")
model = AutoModelForSequenceClassification.from_pretrained("juliensimon/autonlp-imdb-demo-hf-16622775")

def predict(review):
	inputs = tokenizer(review, padding=True, truncation=True, return_tensors="pt")
	outputs = model(**inputs)
	predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
	predictions = predictions.detach().numpy()[0]
	index = np.argmax(predictions)
	score = predictions[index]
	return "This review is {:.2f}% {}".format(100*score, "negative" if index==0 else "positive")

iface = gr.Interface(fn=predict, inputs="text", outputs="text")
iface.launch()