Update app.py

app.py

@@ -15,7 +15,6 @@ tokenizer = AutoTokenizer.from_pretrained("truongghieu/deci-finetuned", trust_re
 model = AutoModelForCausalLM.from_pretrained("truongghieu/deci-finetuned", trust_remote_code=True, quantization_config=bnb_config)
 
 # Move the model to the GPU if available
-model.to(device)
 
 generation_config = GenerationConfig(
     penalty_alpha=0.6,
@@ -32,7 +31,7 @@ generation_config = GenerationConfig(
 # Define a function that takes a text input and generates a text output
 def generate_text(text):
     input_text = text
-    input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)  # Move input to the GPU
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
     output_ids = model.generate(input_ids, generation_config=generation_config)
     output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
     return output_text