bitshrine commited on
Commit
0e0c94e
·
verified ·
1 Parent(s): 69793e1

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -1
tokenizer_config.json CHANGED
@@ -2048,7 +2048,7 @@
2048
  "<end_of_turn>"
2049
  ],
2050
  "bos_token": "<bos>",
2051
- "chat_template": "\n{# Macro used to render JSON elements as text. Used to render tool descriptions in chat #}\n{%- macro render_json(el, indent=4) -%}\n {%- if el is string %}\n{{'\"' + el + '\"'}}\n {%- elif el is mapping %}\n {%- for key, value in el.items() %}\n {%- if value is string %}\n{{ \" \" * indent + '\"' + key + '\": \"' + value + '\"' }}\n {%- elif value is mapping %}\n{{ \" \" * indent + '\"' + key + '\": {' }}\n{{ render_json(value, indent + 4) }}\n{{ \" \" * indent + \"}\" }}\n {%- elif value is sequence %}\n{{ \" \" * indent + '\"' + key + '\": [\n'}}\n {%- for v in value %}\n{{- \" \" * (indent + 4) + render_json(v, indent + 4) }}\n{%- if not loop.last -%},\n{% endif %}\n {%- endfor %} {# FOR LOOP values #}\n{{ '\n' + \" \" * indent + \"]\" }}\n {%- else -%}\n{{ \" \" * indent + '\"' + key + '\" :' + value|string }}\n {%- endif -%}\n{%- if not loop.last %},\n{% endif %}\n {%- endfor %} {# FOR LOOP el.items() #}\n {%- elif el is sequence -%}\n {%- for v in el -%}\n{{\" \" * indent + render_json(v, indent + 4) }}\n{%- if not loop.last -%},\n{% endif %}\n {%- endfor -%}\n {%- else -%}\n{{ \" \" * indent + el|string }}\n {%- endif %}\n{%- endmacro %}\n\n{#- This block checks system prompt and list of tools #}\n{%- if not add_generation_prompt is defined %}\n {%- set add_generation_prompt = false %}\n{%- endif %}\n{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_init_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n {%- set system_init_message = none %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr(\"role\", \"equalto\", \"user\") | list %}\n\n\n{#- This block format full dialogue messages #}\n{{- bos_token }}\n{%- if system_init_message is defined -%}\n{{- \"<start_of_turn>system\" + '\n' + system_init_message}}\n {%- if tools is not none %}\n {{- \"[\" -}}\n {%- for tool in tools %}\n {# {%- set tool = tool.function %} #}\n {{- '{\n' }}\n {{- render_json(tool, 4) }}\n {%- if not loop.last %}\n {{- \"\n,\n\" }}\n {%- else %}\n {{- \"\n\n\" }}\n {% endif %}\n {%- endfor %}\n {{- \"]\" -}}\n {%- else %}\n {{- '\n\n' }}\n {%- endif %}\n{%- else -%}\n{{ \"<start_of_turn>user\" + '\n'}}\n{%- endif -%}\n{{ loop_messages[0]['content'] + '<end_of_turn>\n' }}\n{%- for message in loop_messages[1:] %}\n {%- if message[\"role\"] == \"user\" %}\n {{- \"<start_of_turn>user\" + '\n' + message['content'] + '<end_of_turn>\n' }}\n {%- elif message[\"role\"] == \"model\" %}\n {{- \"<start_of_turn>model\" + '\n' + message['content'] + '<end_of_turn>\n' }}\n {%- elif message[\"role\"] == \"system\" %}\n {{- \"<start_of_turn>system\" + '\n' + message['content'] + '<end_of_turn>\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {%- if loop_messages[-1]['role'] == \"user\" or loop_messages[-1]['role'] == \"system\" %}\n{{ '<start_of_turn>model\n' }}\n {%- else %}\n {{- raise_exception(\"For add_generation_prompt=True, the last message role must be 'user' or 'system'.\") }}\n {%- endif %}\n{%- endif %}\n\n",
2052
  "clean_up_tokenization_spaces": false,
2053
  "eos_token": "<eos>",
2054
  "model_max_length": 8192,
 
2048
  "<end_of_turn>"
2049
  ],
2050
  "bos_token": "<bos>",
2051
+ "chat_template": "\n{# Macro used to render JSON elements as text. Used to render tool descriptions in chat #}\n{%- macro render_json(el, indent=4) -%}\n {%- if el is string %}\n{{'\"' + el + '\"'}}\n {%- elif el is mapping %}\n {%- for key, value in el.items() %}\n {%- if value is string %}\n{{ \" \" * indent + '\"' + key + '\": \"' + value + '\"' }}\n {%- elif value is mapping %}\n{{ \" \" * indent + '\"' + key + '\": {' }}\n{{ render_json(value, indent + 4) }}\n{{ \" \" * indent + \"}\" }}\n {%- elif value is sequence %}\n{{ \" \" * indent + '\"' + key + '\": [\n'}}\n {%- for v in value %}\n{{- \" \" * (indent + 4) + render_json(v, indent + 4) }}\n{%- if not loop.last -%},\n{% endif %}\n {%- endfor %} {# FOR LOOP values #}\n{{ '\n' + \" \" * indent + \"]\" }}\n {%- else -%}\n{{ \" \" * indent + '\"' + key + '\" :' + value|string }}\n {%- endif -%}\n{%- if not loop.last %},\n{% endif %}\n {%- endfor %} {# FOR LOOP el.items() #}\n {%- elif el is sequence -%}\n {%- for v in el -%}\n{{\" \" * indent + render_json(v, indent + 4) }}\n{%- if not loop.last -%},\n{% endif %}\n {%- endfor -%}\n {%- else -%}\n{{ \" \" * indent + el|string }}\n {%- endif %}\n{%- endmacro %}\n\n{#- This block checks system prompt and list of tools #}\n{%- if not add_generation_prompt is defined %}\n {%- set add_generation_prompt = false %}\n{%- endif %}\n{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_init_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n {%- set system_init_message = none %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr(\"role\", \"equalto\", \"user\") | list %}\n\n\n{#- This block format full dialogue messages #}\n{{- bos_token }}\n{%- if system_init_message is defined -%}\n{{- \"<start_of_turn>system\" + '\n' + system_init_message}}\n {%- if tools is not none %}\n {{- \"<tools>[\" -}}\n {%- for tool in tools %}\n {# {%- set tool = tool.function %} #}\n {{- '{\n' }}\n {{- render_json(tool, 4) }}\n {%- if not loop.last %}\n {{- \"\n,\n\" }}\n {%- else %}\n {{- \"\n\n\" }}\n {% endif %}\n {%- endfor %}\n {{- \"]</tools>\" -}}\n {%- else %}\n {{- '\n\n' }}\n {%- endif %}\n{%- else -%}\n{{ \"<start_of_turn>user\" + '\n'}}\n{%- endif -%}\n{{ loop_messages[0]['content'] + '<end_of_turn>\n' }}\n{%- for message in loop_messages[1:] %}\n {%- if message[\"role\"] == \"user\" %}\n {{- \"<start_of_turn>user\" + '\n' + message['content'] + '<end_of_turn>\n' }}\n {%- elif message[\"role\"] == \"model\" %}\n {{- \"<start_of_turn>model\" + '\n' + message['content'] + '<end_of_turn>\n' }}\n {%- elif message[\"role\"] == \"system\" %}\n {{- \"<start_of_turn>system\" + '\n' + message['content'] + '<end_of_turn>\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {%- if loop_messages[-1]['role'] == \"user\" or loop_messages[-1]['role'] == \"system\" %}\n{{ '<start_of_turn>model\n' }}\n {%- else %}\n {{- raise_exception(\"For add_generation_prompt=True, the last message role must be 'user' or 'system'.\") }}\n {%- endif %}\n{%- endif %}\n\n",
2052
  "clean_up_tokenization_spaces": false,
2053
  "eos_token": "<eos>",
2054
  "model_max_length": 8192,