Add chat template

README.md

@@ -64,6 +64,33 @@ We used [OpenAI's Chat Markup Language (ChatML)](https://github.com/openai/opena
 
 This means that, e.g., in [oobabooga](https://github.com/oobabooga/text-generation-webui/) the "`MPT-Chat`" instruction template should work, as it also uses ChatML.
 
+This formatting has also been set as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating),
+which means that lists of messages can be formatted for you with the `apply_chat_template()` method:
+
+```python
+chat = [
+  {"role": "user", "content": "Hello, how are you?"},
+  {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
+  {"role": "user", "content": "I'd like to show off how chat templating works!"},
+]
+tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+```
+
+which will yield:
+
+```
+<|im_start|>user
+Hello, how are you?<|im_end|>
+<|im_start|>assistant
+I'm doing great. How can I help you today?<|im_end|>
+<|im_start|>user
+I'd like to show off how chat templating works!<|im_end|>
+<|im_start|>assistant
+```
+
+If you use `tokenize=True` and `return_tensors="pt"` instead, then you will get a tokenized 
+and formatted conversation ready to pass to `model.generate()`.
+
 ## Example Prompt Exchange
 
 ```
@@ -173,4 +200,4 @@ Commodity cost was ~$400.
       archivePrefix={arXiv},
       primaryClass={cs.AI}
 }
-```
+```

tokenizer_config.json

@@ -45,6 +45,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "legacy": true,