feat: add Exaone3 chat_template

[shing100]

Description

Added exaone template to support new upcoming exaone models

[chiwanpark]

IMHO, there is a patch to load the chat template from model (#1970); thus, we do not need to add the chat template for a specific model.

[shing100]

It's very good.
But is it possible to apply Exaone template to the llama base model without this PR?

[NanoCode012]

@shing100 , yep! You can see this example:

axolotl/docs/dataset-formats/conversation.qmd

Lines 150 to 160 in 28e7e44

	4. Using a custom jinja template on OpenAI messages format, training on all assistant messages.
	```yaml
	# chat_template: jinja # `jinja` will be implied if the `chat_template_jinja` is set and this field is empty
	chat_template_jinja: "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}"
	datasets:
	- path: ...
	type: chat_template
	roles_to_train: ["assistant"]
	```

This way, we don't need to manually merge/add every model's template.

We're currently trying to merge a few PRs soon, and I hope we can get that one in too!

[shing100]

@NanoCode012 Thanks!

[NanoCode012]

@shing100 , I merged #1970 . Please give it a try! I will close this PR for now.

[winglian]

thanks @shing100 !

[shing100]

@NanoCode012 @winglian I just saw the message. I reset it again. Thank you!