Update app.py

app.py

@@ -88,7 +88,7 @@ def interact(user_input, history, interaction_count):
         
         # Generate response using selected model
         input_ids = tokenizer(prompt, return_tensors='pt').input_ids.to("cuda")
-        chat_history_ids = model.generate(input_ids, max_new_tokens=100, pad_token_id=tokenizer.eos_token_id, temperature=0.0)
+        chat_history_ids = model.generate(input_ids, max_new_tokens=100, pad_token_id=tokenizer.eos_token_id, temperature=0.1)
         response = tokenizer.decode(chat_history_ids[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
         
         # Update chat history with generated response