Update app.py

set model to HuggingFaceTB/SmolLM2-135M-Instruct. 1.7B took an eternity to respond. In a production environment, 1.7B would be used and hosted in a separate environment obviously.

app.py

@@ -6,9 +6,9 @@ import torch
 
 MAX_NEW_TOKENS = 600
 
-# MODEL="HuggingFaceTB/SmolLM2-135M-Instruct"
+MODEL="HuggingFaceTB/SmolLM2-135M-Instruct"
 # MODEL="HuggingFaceTB/SmolLM2-360M-Instruct"
-MODEL="HuggingFaceTB/SmolLM2-1.7B-Instruct"
+# MODEL="HuggingFaceTB/SmolLM2-1.7B-Instruct"
 TEMPERATURE = 0.6
 TOP_P = 0.95
 REPETITION_PENALTY = 1.2