Update app.py

app.py

@@ -71,11 +71,12 @@ def chat(id, npc, prompt):
     # model inference
 
     if check(model_name):
-        prom = ""
+        prom = prompt
         inputs = tokenizer(prom, return_tensors="pt")["input_ids"]
         outputs = model.generate(inputs, max_new_tokens=100)
         print(tokenizer.decode(outputs[0]))
         output = outputs[len(prom):-1]
+        print(output)
     else:
         output = "no model"