with torch.no_grad():
    logits = model(input_ids).logits[:, -1, :]
    probs = torch.nn.functional.softmax(logits, dim=-1)
    
    # Get top probability candidates
    top_probs, top_indices = torch.topk(probs, 50)
    
predictions = []
for idx, prob in zip(top_indices[0], top_probs[0]):
    word = tokenizer.decode([idx]).strip()
    
    # Filter out empty strings or byte-fallback artifacts like <0x..>
    if len(word) > 0 and not re.search(r'<0x[0-9A-Fa-f]+>', word):
        predictions.append((word, prob.item()))
        
    if len(predictions) == 5:
        break
        
return predictions