Files
functionary-small-v2.4/tokenizer_config.json

83 lines
15 KiB
JSON
Raw Permalink Normal View History

{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"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 -%}\
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 8192,
"pad_token": "</s>",
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}