[Feature Request] Get chat template from GGUF's tokenizer.chat_template key #1236
Description
I think it will be better than manually adding chat templates of newly released models. Also it will be awesome it it auto set's the correct chat template when an object of the llama class is created.
It just need to parse the value which is generally in the format (for example: this is gemma's chat_template saved in tokenizer.chat_template)
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
' + message['content'] | trim + '<end_of_turn>
' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
'}}{% endif %}
llama.cpp server already supports this.