functionary-medium-v2.4-AWQ / tokenizer_config.json
jeffreymeetkai's picture
Update tokenizer_config.json
f98c87b verified
raw
history blame
15.4 kB
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<|from|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|recipient|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<|content|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<|stop|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|from|>",
"<|recipient|>",
"<|content|>",
"<|stop|>"
],
"bos_token": "<s>",
"chat_template": "{# version=v2 #}{%- macro append_new_param_info(param_declaration, comment_info, examples_info, depth) -%}\n {%- set offset = \"\" -%}\n {%- if depth >= 1 -%}\n {%- set offset = \" \" * depth -%}\n {%- endif -%}\n {%- if comment_info != \"<|NONE|>\" -%}\n {{ \"\\n\" + offset + comment_info }}\n {%- if examples_info | length > 0 -%}\n {# Append each example info #}\n {%- for example in examples_info -%}\n {{ \"\\n\" + offset + \"// \" + example|string|replace(\"'\", '\"') }}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n {{ \"\\n\" + offset + param_declaration }}\n{%- endmacro -%}\n\n{%- macro convert_data_type(param_type) -%}\n {%- if param_type == \"integer\" or param_type == \"float\" -%}\n {{ \"number\" }}\n {%- else -%}\n {{ param_type }}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_param_type(param) -%}\n {%- set param_type = \"any\" -%}\n\n {%- if \"type\" in param -%}\n {%- set raw_param_type = param[\"type\"] -%}\n {%- if raw_param_type is iterable and raw_param_type is not string -%}\n {%- set param_type = raw_param_type | join(\" | \") -%}\n {%- else -%}\n {%- set param_type = raw_param_type -%}\n {%- endif -%}\n {{ convert_data_type(param_type) }}\n {%- elif \"oneOf\" in param -%}\n {%- set one_of_types = param[\"oneOf\"]|selectattr(\"type\", \"defined\")|list -%}\n {%- set one_of_types = one_of_types|map(attribute=\"type\")|unique|list -%}\n {{ convert_data_type(one_of_types | join(\" | \")) }}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_format_param(param) -%}\n {%- if \"format\" in param -%}\n {{ param[\"format\"] }}\n {%- elif \"oneOf\" in param -%}\n {%- set formats = [] -%}\n {%- for item in param[\"oneOf\"] -%}\n {%- if \"format\" in item -%}\n {%- if item[\"format\"] == param[\"oneOf\"][-1][\"format\"] -%}\n {{ item[\"format\"] }}\n {%- else -%}\n {{ item[\"format\"] + \" or \"}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ \"<|NONE|>\" }}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_param_info(param) -%}\n {%- set param_type = param.get(\"type\", \"any\") -%}\n {%- set format_param = get_format_param(param) -%}\n\n {%- if \"description\" in param or \"default\" in param or format_param != \"<|NONE|>\" or param[\"maximum\"] or param[\"minimum\"] or param[\"maxLength\"] or param[\"minLength\"] -%}\n {{ \"//\" }}\n {%- if \"description\" in param -%}\n {%- set desc = param[\"description\"] -%}\n {%- if not desc.endswith(\".\") -%}\n {%- set desc = desc + \".\" -%}\n {%- endif -%}\n {{ \" \" + desc }}\n {%- endif -%}\n\n {%- if \"default\" in param -%}\n {%- set default_value = param[\"default\"] -%}\n {%- if param_type == \"string\" -%}\n {%- set default_value = '\"' ~ default_value ~ '\"' -%}\n {%- endif -%}\n {{ \" Default=\" ~ default_value ~ \".\" }}\n {%- endif -%}\n\n {%- set format_param = get_format_param(param) -%}\n {%- if format_param != \"<|NONE|>\" -%}\n {{ \" Format=\" ~ format_param }}\n {%- endif -%}\n\n {%- for field, field_name in [(\"maximum\", \"Maximum\"), (\"minimum\", \"Minimum\"), (\"maxLength\", \"Maximum length\"), (\"minLength\", \"Minimum length\")] -%}\n {%- if field in param -%}\n {{ \" \" + field_name ~ \"=\" ~ param[field] }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ \"<|NONE|>\"}}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_enum_option_str(enum_options) -%}\n {%- for v in enum_options -%}\n {%- if v is string -%}\n {{ '\"' + v + '\"' }}\n {%- else -%}\n {{ v }}\n {%- endif -%}\n {%- if enum_options|length > 0 and v != enum_options[-1] -%}\n {{ \" | \" }}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n\n{%- macro get_array_typescript(param_name, param_dic, depth) -%}\n {%- set offset = '' -%}\n {%- if depth >= 1 -%}\n {%- set offset = \" \" * depth -%}\n {%- endif -%}\n {%- set items_info = param_dic.get('items', {}) -%}\n\n {%- if items_info|length == 0 -%}\n {%- if param_name is not none -%}\n {{ \"\\n\" + offset + param_name + \": []\" }}\n {%- else -%}\n {{ \"\\n\" + offset + \"[]\" }}\n {%- endif -%}\n {%- else -%}\n {%- set array_type = get_param_type(items_info) -%}\n {%- if array_type == 'object' -%}\n {%- if param_name -%}\n {{ \"\\n\" + offset + param_name + \": {\" }}\n {%- else -%}\n {{ \"\\n\" + offset + \"{\" }}\n {%- endif -%}\n {{ get_parameter_typescript(items_info.get('properties', {}), items_info.get('required', []), depth + 1) -}}\n {{- \"\\n\" + offset + \"}[]\" }}\n {%- elif array_type == 'array' -%}\n {%- set item_info = get_array_typescript(None, items_info, depth + 1) -%}\n {%- if not param_name -%}\n {{ \"\\n\" + item_info + \"[]\" }}\n {%- else -%}\n {{ \"\\n\" + offset + param_name + \": \" + item_info|trim + \"[]\" }}\n {%- endif -%}\n {%- else -%}\n {%- if 'enum' in items_info -%}\n {%- set item_type = get_enum_option_str(items_info['enum']) -%}\n {%- if param_name is none -%}\n {{ \"(\" + item_type + \")[]\"}}\n {%- else -%}\n {{ \"\\n\" + offset + param_name + \": (\" + item_type + \")[]\" }}\n {%- endif -%}\n {%- else -%}\n {%- if param_name is none -%}\n {{ \"\\n\" + array_type + \"[]\" }}\n {%- else -%}\n {{ \"\\n\" + offset + param_name + \": \" + array_type + \"[],\" }}\n {%- endif -%}\n {%- endif -%}\n {%- endif -%}\n {%- endif -%}\n{%- endmacro -%}\n\n{%- macro get_parameter_typescript(properties, required_params, depth=0) -%}\n {%- set res = \"\" -%}\n {%- for param_name, param in properties.items() -%}\n {%- if param is mapping -%}\n {%- set comment_info = get_param_info(param) -%}\n {# Param Examples #}\n {%- set examples_info = [] -%}\n {%- if \"examples\" in param -%}\n {%- set examples_info = [\"Example \" + param_name + \":\"] -%}\n {%- set examples_info = examples_info + param[\"examples\"] -%}\n {%- endif -%}\n\n {# Param Name declaration #}\n {%- set param_declaration = param_name -%}\n {%- if required_params is iterable and param_name not in required_params -%}\n {%- set param_declaration = param_declaration + \"?\" -%}\n {%- endif -%}\n\n {%- set param_type = get_param_type(param) -%}\n\n {# Handle indentation based on depth #}\n {%- set offset = \"\" -%}\n {%- if depth >= 1 -%}\n {%- set offset = \" \" * depth -%}\n {%- endif -%}\n\n {%- if param_type == \"object\" -%}\n {%- if comment_info != \"<|NONE|>\" -%}\n {{ \"\\n\" + offset + comment_info }}\n {%- endif -%}\n {%- if examples_info|length > 0 -%}\n {%- for example in examples_info -%}\n {{ \"\\n\" + offset + \"// \" + example|string|replace(\"'\", '\"') }}\n {%- endfor -%}\n {%- endif -%}\n {%- set param_declaration = param_declaration + \": {\" -%}\n {{ \"\\n\" + offset + param_declaration -}}\n {{- get_parameter_typescript(param.get(\"properties\", {}), param.get(\"required\", []), depth + 1) -}}\n {{- \"\\n\" + offset + \"},\" }}\n {%- elif param_type == \"array\" -%}\n {%- set item_info = param.get(\"items\", {}) -%}\n {%- if \"type\" not in item_info -%}\n {%- set param_declaration = param_declaration + \": [],\" -%}\n {{ append_new_param_info(param_declaration, comment_info, examples_info, depth) }}\n {%- else -%}\n {%- if comment_info != \"<|NONE|>\" -%}\n {{ \"\\n\" + offset + comment_info }}\n {%- endif -%}\n {%- if examples_info|length > 0 -%}\n {%- for example in examples_info -%}\n {{ \"\\n\" + offset + \"// \" + example|string|replace(\"'\", '\"') }}\n {%- endfor -%}\n {%- endif -%}\n {%- set array_declaration = get_array_typescript(param_declaration, param, depth) -%}\n {%- if not array_declaration.endswith(\",\") -%}\n {%- set array_declaration = array_declaration + \",\" -%}\n {%- endif -%}\n {{ array_declaration}}\n {%- endif -%}\n {%- else -%}\n {%- if \"enum\" in param -%}\n {%- set param_type = get_enum_option_str(param[\"enum\"]) -%}\n {%- endif -%}\n {%- if \"nullable\" in param and param[\"nullable\"] -%}\n {%- set param_type = param_type + \" | null\" -%}\n {%- endif -%}\n {%- set param_declaration = param_declaration + \": \" + param_type + \",\" -%}\n {{ append_new_param_info(param_declaration, comment_info, examples_info, depth) }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n{%- endmacro -%}\n\n{%- macro generate_schema_from_functions(functions, namespace='functions') -%}\n {{ \"// Supported function definitions that should be called when necessary.\\n\" -}}\n {{- \"namespace \" + namespace + \" {\\n\\n\" -}}\n\n {%- for function in functions -%}\n {%- if function.get(\"function\") is not none -%}\n {%- set function = function.get(\"function\") -%}\n {%- endif -%}\n\n {%- set function_name = function.get(\"name\") -%}\n {%- if function_name is not none -%}\n {%- set description = function.get('description', '') -%}\n {%- set parameters = function.get('parameters', {}) -%}\n {{- \"// \" + description + \"\\n\" -}}\n {{- \"type \" + function_name -}}\n {%- if parameters is not none and parameters.get(\"properties\") is not none -%}\n {{- \" = (_: {\" -}}\n {%- set required_params = parameters.get(\"required\", []) -%}\n {{ get_parameter_typescript(parameters.get(\"properties\"), required_params, 0) -}}\n {{- \"\\n}) => any;\\n\\n\" }}\n {%- else -%}\n {{ \" = () => any;\\n\\n\" }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {{ \"} // namespace \" + namespace }}\n{%- endmacro -%}\n{%- if not tools -%}\n {%- set tools = [] -%}\n{%- endif -%}\n{{ bos_token + '<|from|>system\\n<|recipient|>all\\n<|content|>' + generate_schema_from_functions(tools) -}}\n{%- if tools|length > 0 and tools|selectattr(\"type\", \"equalto\", \"code_interpreter\")|list|length > 0 -%}\n {{ '\\n<|from|>system\\n<|recipient|>all\\n<|content|>When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 60.0 seconds. The drive at \\'/mnt/data\\' can be used to save and persist user files.' }}\n{%- else -%}\n {{ \"\\n<|from|>system\\n<|recipient|>all\\n<|content|>A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. The assistant calls functions with appropriate input when necessary\" }}\n{%- endif -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'user' or message['role'] == 'system' -%}\n {{ '\\n<|from|>' + message['role'] + '\\n<|recipient|>all\\n<|content|>' + message['content'] }}\n {%- elif message['role'] == 'tool' -%}\n {{ '\\n<|from|>' + message['name'] + '\\n<|recipient|>all\\n<|content|>' + message['content'] }}\n {%- else -%}\n {%- if message['content'] -%}\n {{ \"\\n<|from|>\" + message['role'] + \"\\n<|recipient|>all\\n<|content|>\" + message['content'] }}\n {%- endif -%}\n {%- if 'tool_calls' in message and message['tool_calls'] is not none -%}\n {%- for tool_call in message['tool_calls'] -%}\n {{ '\\n<|from|>' + message['role'] + '\\n<|recipient|>' + tool_call['function']['name'] + '\\n<|content|>' + tool_call['function']['arguments'] }}\n {%- endfor -%}\n {%- endif -%}\n {{ \"<|stop|>\" }}\n {%- endif -%}\n{%- endfor -%}\n{% if add_generation_prompt %}{{ '\\n<|from|>assistant\\n<|recipient|>' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"max_length": 8192,
"model_max_length": 8192,
"pad_to_multiple_of": null,
"pad_token": "</s>",
"pad_token_type_id": 0,
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": false
}