Update app.py

app.py

@@ -14,7 +14,7 @@ model, tokenizer = FastLanguageModel.from_pretrained(
     load_in_4bit = True,
     token= READ_HF    
 )
-FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+
 
 
 alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
@@ -77,7 +77,7 @@ Category List : ["Dairy & Eggs", "Beverages & Snacks", "Cleaning & Hygiene", "Gr
 
 @spaces.GPU()
 def chunk_it(inventory_list, user_input_text):
-    model.to('cuda')
+    FastLanguageModel.for_inference(model) # Enable native 2x faster inference
     inputs = tokenizer(
         [
             alpaca_prompt.format(
@@ -104,7 +104,7 @@ iface = gr.Interface(
         gr.Textbox(label="user_input_text", lines=3),
         gr.Textbox(label="inventory_list", lines=5)
     ],
-    outputs="text",
+    outputs=gr.Textbox(label="output", lines=23),
     title="Testing",
 )