| import torch | |
| import numpy as np | |
| import gradio as gr | |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification | |
| 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 revied os {:.3f}% {}".format(100*score, "negative" if index == 0 else "positive") | |
| iface = gr.Interface(fn=predict, inputs='text', outputs='text') | |
| iface.launch() | |