Update app.py

app.py

@@ -15,25 +15,25 @@ model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
 
 
 def run_generation(user_text, top_p, temperature, top_k, max_new_tokens):
-   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.
+    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.
 
-### Instruction:
-{}
-
-### Input:
-{}
-
-### Response:
-{}"""
+    ### Instruction:
+    {}
+    
+    ### Input:
+    {}
+    
+    ### Response:
+    {}"""
 
     inputs = tokenizer(
-[
+    [
     alpaca_prompt.format(
         "You are an AI assistant. Please ensure that the answers conclude with an end-of-sequence (EOS) token.", # instruction
         user_text, # input goes here
         "", # output - leave this blank for generation!
     )
-], return_tensors = "pt",return_dict=True)
+    ], return_tensors = "pt",return_dict=True)
 
     # Start generation on a separate thread, so that we don't block the UI. The text is pulled from the streamer
     # in the main thread. Adds timeout to the streamer to handle exceptions in the generation thread.