updated app.py.

app.py

@@ -7,7 +7,7 @@ client = InferenceClient(
 
 punctuation_marks = [".", "!", "?"]
 def generate(
-    prompt, history, temperature=0.2, max_new_tokens=256, top_p=0.8, repetition_penalty=1.0,
+    prompt, temperature=0.2, max_new_tokens=256, top_p=0.8, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -31,7 +31,6 @@ def generate(
         output += response.token.text
     while output and output[-1] not in punctuation_marks:
       output = output[:-1]
-        # yield output
     return output