YuLan-Mini / tokenizer_config.json
IvanHU's picture
Upload tokenizer
b9cb38c verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"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
},
"102": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "<reasoning_step>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"104": {
"content": "<|start_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"105": {
"content": "<|end_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"106": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{% if messages[0]['role'] == 'system' %}\n {% set offset = 1 %}\n{% else %}\n {% set offset = 0 %}\n{% endif %}\n\n{{ bos_token }}\n{% for message in messages %}\n {% if (message['role'] == 'user') != (loop.index0 % 2 == offset) %}\n {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n {% endif %}\n\n {{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}\n{% endfor %}\n\n{% if add_generation_prompt %}\n {{ '<|start_header_id|>' + 'assistant' + '<|end_header_id|>\n\n' }}\n{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"extra_special_tokens": {},
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}