Update app.py

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import transformers
 from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 
 # Load the model and tokenizer
@@ -9,7 +10,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 # Define the function to generate response
 def generate_response(prompt):
     instruction = f"### Instruction:\n{prompt}\n\n### Response:\n"
-    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=256)
+    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=64)
     result = pipe(instruction)
     generated_text = result[0]['generated_text'][len(instruction):].strip()
     return generated_text