Minitron-4B-Base / tokenizer_config.json
PaulD's picture
Upload tokenizer
4b4ad69 verified
{
"add_bos_token": false,
"add_eos_token": false,
"add_prefix_space": true,
"added_tokens_decoder": {
"1": {
"content": "<unk>",
"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
},
"3": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{% set loop_messages = messages %}\n{% for message in loop_messages %}\n{% set content = message['role']+'\n'+ message['content'] + '\n' %}\n{% if message['role'] == 'System' %}\n{% set content = '<extra_id_0>' + content %}\n{% else %}\n{% set content = '<extra_id_1>' + content %}\n{% endif %}\n{{ content }}\n{% endfor %}\n{% if add_generation_prompt %}\n{{ '<extra_id_1>Assistant' }}\n\n{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}