Update app.py

app.py

@@ -22,7 +22,7 @@ model.load_adapter(adapter_path)
 
 def inference(prompt):
 
-  pipe = pipeline(task="text-generation",model=model,tokenizer=tokenizer,max_length=200)
+  pipe = pipeline(task="text-generation",model=model,tokenizer=tokenizer,max_length = 100)
   result = pipe(f"<s>[INST] {prompt} [/INST]")
   return result[0]['generated_text']