dev

app.py

@@ -251,9 +251,6 @@ def predict(text):
     #initialize_weights(model)
     tokenizer = AutoTokenizer.from_pretrained('shorecode/t5-efficient-tiny-nh8-summarizer')
     inputs = tokenizer(text, padding='max_length', max_length=512, truncation=True)
-    if torch.cuda.is_available():
-        model = model.to('cuda')
-        inputs = {key: value.to('cuda') for key, value in inputs.items()}    
     with torch.no_grad():  # Disable gradient calculation for inference
         outputs = model.generate(inputs)
     predictions = tokenizer.decode(outputs[0], skip_special_tokens=True)