Update app.py

app.py

@@ -75,7 +75,7 @@ def chat(id, npc, 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]
+        output = tokenizer.decode(outputs[0])[len(prom):-1]
         print(output)
     else:
         output = "no model"