Update utils/generation.py

utils/generation.py

@@ -72,7 +72,7 @@ def generate_answer(query, retrieved_chunks, model=model, tokenizer=tokenizer):
     inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
     outputs = model.generate(
         **inputs,
-        max_new_tokens=512,
+        #max_new_tokens=512,
         num_return_sequences=1,
         no_repeat_ngram_size=2
     )