Update app.py

app.py

@@ -55,7 +55,7 @@ def generate_answer(question):
     #inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
     inputs = tokenizer(question, return_tensors="pt")
     inputs.to("cuda")
-    outputs = model.generate(**inputs, max_length=2048, num_return_sequences=1, do_sample=True)
+    outputs = model.generate(**inputs, max_length=8192, num_return_sequences=1, do_sample=True)
     answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return answer