qwen2-maritalk-tokenizer-v2 / tokenizer_config.json
hugo's picture
Upload tokenizer
2d096ae verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": null,
"chat_template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}Uma conversa entre um usuário curioso e uma assistente de inteligência artificial. A assistente fornece respostas úteis, detalhadas e educadas às perguntas do usuário. {% elif message['role'] == 'system' %}{{ message['content'] + ' ' }}{% endif %}{% if message['role'] == 'user' %}USUÁRIO: {{ message['content'] }} {% elif message['role'] == 'assistant' %}ASSISTENTE: {{ (message['content'] or '') }}{% if 'tool_calls' in message %}<multiplefunctions>\n{% for tool_call in message['tool_calls'] %} <functioncall> {\"name\": \"{{ tool_call['function']['name'] }}\", \"arguments\": {{ tool_call['function']['arguments'] }}} </functioncall>\n{% endfor %}</multiplefunctions>{% endif %}{{ eos_token }}{% elif message['role'] == 'tool' %}{{ 'FUNCTION_RESPONSE: ' + message['content'] + ' '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTENTE:' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}