from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import torch.nn.functional as F

# Repository ID
repo_id = "aderohmatmaulana98/tweet-classification"
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Load Tokenizer & Model
# It's highly recommended to load the tokenizer from the base model for consistent normalization
tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base", use_fast=False, normalization=True)
model = AutoModelForSequenceClassification.from_pretrained(repo_id)
model.to(device)
model.eval()

def clean_text(text):
    """Normalize text to match training conditions"""
    text = text.replace("{{USERNAME}}", "@USER")
    text = text.replace("{{URL}}", "HTTPURL")
    return " ".join(text.split())

# Input text
text = "The new science breakthrough is amazing!"
cleaned_text = clean_text(text)

inputs = tokenizer(
    cleaned_text, 
    return_tensors="pt", 
    truncation=True, 
    max_length=128,
    padding="max_length"
)
inputs = {k: v.to(device) for k, v in inputs.items()}

with torch.no_grad():
    outputs = model(**inputs)
    probs = F.softmax(outputs.logits, dim=-1)

pred_id = torch.argmax(probs, dim=-1).item()
confidence = torch.max(probs).item()

# Label mapping from model config
label = model.config.id2label[pred_id]
print(f"Predicted: {label}")
print(f"Confidence: {confidence*100:.2f}%")

🛠️ Training Details

Max Length: 128
Batch Size: 32 (effective)
Learning Rate: 1e-5
Optimizer: AdamW
Training Technique: Mixed Precision (FP16), Oversampling for Imbalance.