Views
No views yet
bert-base-uncased) for sentiment analysis on the IMDb movie review dataset. The model classifies text into:bert-base-uncasedtransformers:1from transformers import BertTokenizer, BertForSequenceClassification
2import torch
3import torch.nn.functional as F
4
5model_name = "saubhagya122k4/bert-sentiment-analysis"
6
7tokenizer = BertTokenizer.from_pretrained(model_name)
8model = BertForSequenceClassification.from_pretrained(model_name)
9model.eval()
10
11text = "This movie was fantastic! I really enjoyed it."
12
13inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=70)
14
15with torch.no_grad():
16 outputs = model(**inputs)
17 probs = F.softmax(outputs.logits, dim=1)
18 predicted = torch.argmax(probs, dim=1).item()
19
20labels = {0: "Positive", 1: "Negative"}
21print(f"Sentiment: {labels[predicted]}")bert-base-uncased