Fix Bug

app.py

@@ -112,7 +112,7 @@ def get_completion(
         model=model,
         messages=messages,
         temperature=temperature,  # this is the degree of randomness of the model's output
-        max_new_tokens=250,  # this is the number of new tokens being generated
+        max_tokens=250,  # this is the number of new tokens being generated
         top_p=top_p,
         top_k=top_k,
         stream=stream,
@@ -256,7 +256,7 @@ def generate(
         qa_prompt,
         system_prompt=system_prompt,
         #stream=True,
-        max_tokens=max_new_tokens,
+        max_new_tokens=max_new_tokens,
         temperature=temperature,
         top_k=top_k,
         top_p=top_p,