fix max tokens

app.py

@@ -15,14 +15,14 @@ def decomp_create_prompt(input_data: str) -> str:
     return prompt
 
 
-pipe = pipeline(model="ejschwartz/decaf-v1-22b-4bit", return_full_text=False, max_new_tokens=2000)
+pipe = pipeline(model="ejschwartz/decaf-v1-22b-4bit", return_full_text=False)
 pipe.model.to("cuda")
 
 @spaces.GPU
 def generate(text):
     print(f"Generating text... {text}")
     prompt = decomp_create_prompt(text)
-    return pipe(prompt)[0]['generated_text']
+    return pipe(prompt, max_new_tokens=2000)[0]['generated_text']
 
 demo = gr.Interface(fn=generate, inputs="text", outputs="text")
 demo.launch()