add chat_template in tokenizer_config.json

I think you forgot to add chat_template in tokenizer_config.json.
I picked chat_template from deepseek-llm-67b-chat

The response looks good.

```
<｜begin▁of▁sentence｜>User: hello

Assistant: Hello! How can I assist you today?<｜end▁of▁sentence｜>User: who are you?

Assistant: I am an artificial intelligence language model developed by OpenAI. I am designed to assist with a wide range of tasks, including answering questions and providing information on a variety of topics. How can I assist you today?<｜end▁of▁sentence｜>User: tell me a joke?

Assistant: Sure! Here's a joke for you:

Why don't scientists trust atoms?

Because they make up everything!<｜end▁of▁sentence｜>User: one more

Assistant:Sure! Here's another joke for you:

Why don't some couples go to the gym?

Because some relationships don't work out!
```

tokenizer_config.json

@@ -30,5 +30,6 @@
   },
   "sp_model_kwargs": {},
   "unk_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
   "tokenizer_class": "LlamaTokenizerFast"
-}
+}