chat_template.jinja

{{- bos_token }}

{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
    {%- if messages[0]['content'] is string %}
        {%- set system_message = messages[0]['content']|trim %}
    {%- elif messages[0]['content'] is iterable and messages[0]['content'][0]['type'] == 'text' %}
        {%- set system_message = messages[0]['content'][0]['text']|trim %}
    {%- else %}
        {{- raise_exception("System message content must be a string or contain text type!") }}
    {%- endif %}
    {%- set messages = messages[1:] %}
{%- else %}
    {{- raise_exception("A system message is required but not provided!") }}
{%- endif %}

{#- System message #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{{- system_message }}

{#- Check for scene message and handle it specially #}
{%- if messages and messages[0]['role'] == 'scene' %}
    {{- "\n\n<|scene_desc_start|>\n" }}
    {%- if messages[0]['content'] is string %}
        {{- messages[0]['content'] | trim }}
    {%- elif messages[0]['content'] is iterable %}
        {%- for content_item in messages[0]['content'] %}
            {%- if content_item['type'] == 'text' %}
                {%- set text_content = content_item['text'] | trim %}
                {{- text_content }}
                {%- if loop.first and not loop.last %}
                    {{- "\n\n" }}            
                {%- endif %}
                {%- if not loop.first and not loop.last and messages[0]['content'][loop.index]['type'] != 'audio' %}
                    {{- "\n" }}
                {%- endif %}
            {%- elif content_item['type'] == 'audio' %}
                {{- ' <|audio_out_bos|><|AUDIO_OUT|><|audio_eos|>' }}
                {%- if not loop.last %}
                    {{- "\n" }}
                {%- endif %}
            {%- endif %}
        {%- endfor %}
    {%- endif %}
    {{- "\n<|scene_desc_end|>" }}
    {%- set messages = messages[1:] %}
{%- endif %}

{{- "<|eot_id|>" }}

{#- Loop through all messages #}
{%- for message in messages %}
    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}
    {%- if message['role'] == 'assistant' %}
        {%- if message['content'] is not iterable or message['content'][0]['type'] != 'audio' %}
            {{- raise_exception("Assistant messages must contain audio content only!") }}
        {%- endif %}
        {{- '<|audio_out_bos|><|AUDIO_OUT|><|audio_eos|>' }}
    {%- else %}
        {%- if message['content'] is string %}
            {{- message['content'] | trim }}
        {%- elif message['content'] is iterable %}
            {%- for content_item in message['content'] %}
                {%- if content_item['type'] == 'text' %}
                    {{- content_item['text'] | trim }}
                {%- endif %}
            {%- endfor %}
        {%- endif %}
    {%- endif %}
    {{- '<|eot_id|>' }}
{%- endfor %}

{%- if add_generation_prompt %}
    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n<|audio_out_bos|>' }}
{%- endif %}