Gunulhona commited on
Commit
cd7a56d
·
verified ·
1 Parent(s): 4af3491

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -1
tokenizer_config.json CHANGED
@@ -1744,7 +1744,7 @@
1744
  "<end_of_turn>"
1745
  ],
1746
  "bos_token": "<bos>",
1747
- "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] not in ['user', 'assistant', 'model', 'system'] or (loop.index0 > 0 and message['role'] != 'system' and message['role'] == messages[loop.index0 - 1]['role']) %}{{ raise_exception('Invalid role or role sequence') }}{% endif %}{{ '<start_of_turn>' + message['role'] + '\n' + message['content'] | trim + '<end_of_turn>\n' if message['role'] != 'system' else message['content'] + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<start_of_turn>model\n' }}{% endif %}",
1748
  "clean_up_tokenization_spaces": false,
1749
  "eos_token": "<eos>",
1750
  "model_max_length": 2048,
 
1744
  "<end_of_turn>"
1745
  ],
1746
  "bos_token": "<bos>",
1747
+ "chat_template": "{{ bos_token }}\n{%- set ns = namespace(has_system=false) -%}\n{%- if messages[0]['role'] == 'system' -%}\n {%- set ns.has_system = true -%}\n {{ '<start_of_turn>system\n' }}\n {%- if messages[0]['content'] is string -%}\n {{ messages[0]['content'] | trim }}\n {%- else -%}\n {{ messages[0]['content'][0]['text'] | trim }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if message['role'] == 'assistant' -%}\n {%- set role = \"model\" -%}\n {%- elif message['role'] == 'system' -%}\n {%- set role = \"system\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
1748
  "clean_up_tokenization_spaces": false,
1749
  "eos_token": "<eos>",
1750
  "model_max_length": 2048,