Refactor to fit model recomended usage

app.py

@@ -33,8 +33,15 @@ streamer = TextIteratorStreamer(tokenizer)
 
 cplusplus = None
 def translate(python):
-    inputs = tokenizer(messages_for(python), return_tensors="pt")
-    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=20)
+    inputs = tokenizer.apply_chat_template(messages_for(python), return_tensors="pt").to(model.device)
+    generation_kwargs = dict(
+                            inputs,
+                            streamer=streamer,
+                            max_new_tokens=1024,
+                            do_sample=False,
+                            pad_token_id=tokenizer.eos_token_id,
+                            eos_token_id=tokenizer.eos_token_id
+                            )
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
     thread.start()
     cplusplus = ""