Update app.py

app.py

@@ -38,12 +38,15 @@ def respond(
     inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
     inputs = inputs.to("cuda")
     
+    print("eos_token_id: ", tokenizer.eos_token_id)
+    
     # Generate response
     generate_ids = model.generate(
         inputs,
         max_length=max_tokens,
         temperature=temperature,
-        top_p=top_p
+        top_p=top_p,
+        eos_token_id=tokenizer.eos_token_id,
     )
     
     # Decode the generated response