Sentiment Classification with Pre-trained Model

This function uses a pre-trained model from the Huggingface Transformers library to classify the sentiment of the input text, determining whether the text is positive or negative.

Technology Stack : Huggingface Transformers

Code Type : The type of code

Code Difficulty : Intermediate

                
                    
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

def classify_sentiment(text, model_name="distilbert-base-uncased-finetuned-sst-2-english"):
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForSequenceClassification.from_pretrained(model_name)
    
    inputs = tokenizer(text, return_tensors="pt")
    outputs = model(**inputs)
    
    _, prediction = torch.max(outputs.logits, dim=1)
    return "positive" if prediction.item() == 1 else "negative"