Add chat template

Will show chat UI in HF inference widget

tokenizer_config.json

@@ -319,5 +319,6 @@
   "eos_token": "<|endoftext|>",
   "model_max_length": 2048,
   "tokenizer_class": "CodeGenTokenizer",
-  "unk_token": "<|endoftext|>"
-}
+  "unk_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+}