Update app.py

app.py

@@ -40,7 +40,8 @@ def text2text(input_text):
     print("Length of input: " + str(len(input_text)))
 
     # Does not seem to care if it goes over 512... humm...
-    outputs = model.generate(input_ids, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.8)
+    # To make it faster generate 100 tokens at a time
+    outputs = model.generate(input_ids, max_new_tokens=100, do_sample=True, temperature=0.7, top_p=0.8)
 
     # Remove <pad> and </s> eof sequence tokens
     model_output_text = tokenizer.decode(outputs[0],skip_special_tokens=True)