tokenizer/chat_template.jinja
| 1 | {{ bos_token }} |
| 2 | {%- if messages[0]['role'] == 'system' -%} |
| 3 | {%- if messages[0]['content'] is string -%} |
| 4 | {%- set first_user_prefix = messages[0]['content'] + ' |
| 5 | |
| 6 | ' -%} |
| 7 | {%- else -%} |
| 8 | {%- set first_user_prefix = messages[0]['content'][0]['text'] + ' |
| 9 | |
| 10 | ' -%} |
| 11 | {%- endif -%} |
| 12 | {%- set loop_messages = messages[1:] -%} |
| 13 | {%- else -%} |
| 14 | {%- set first_user_prefix = "" -%} |
| 15 | {%- set loop_messages = messages -%} |
| 16 | {%- endif -%} |
| 17 | {%- for message in loop_messages -%} |
| 18 | {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%} |
| 19 | {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }} |
| 20 | {%- endif -%} |
| 21 | {%- if (message['role'] == 'assistant') -%} |
| 22 | {%- set role = "model" -%} |
| 23 | {%- else -%} |
| 24 | {%- set role = message['role'] -%} |
| 25 | {%- endif -%} |
| 26 | {{ '<start_of_turn>' + role + ' |
| 27 | ' + (first_user_prefix if loop.first else "") }} |
| 28 | {%- if message['content'] is string -%} |
| 29 | {{ message['content'] | trim }} |
| 30 | {%- elif message['content'] is iterable -%} |
| 31 | {%- for item in message['content'] -%} |
| 32 | {%- if item['type'] == 'image' -%} |
| 33 | {{ '<start_of_image>' }} |
| 34 | {%- elif item['type'] == 'text' -%} |
| 35 | {{ item['text'] | trim }} |
| 36 | {%- endif -%} |
| 37 | {%- endfor -%} |
| 38 | {%- else -%} |
| 39 | {{ raise_exception("Invalid content type") }} |
| 40 | {%- endif -%} |
| 41 | {{ '<end_of_turn> |
| 42 | ' }} |
| 43 | {%- endfor -%} |
| 44 | {%- if add_generation_prompt -%} |
| 45 | {{'<start_of_turn>model |
| 46 | '}} |
| 47 | {%- endif -%} |
| 48 | |