ibrain_0003 / tokenizer_config.json
qbitmaze's picture
Upload tokenizer
2e7ed1e verified
{
"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": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% if messages[0]['from'] == 'system' %}{{ messages[0]['value'] + '\n' }}{% set loop_messages = messages[1:] %}{% else %}{{ 'You are a helpful assistant to the user\n' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['from'] == 'human' %}{{ '>>> User: ' + message['value'] + '\n' }}{% elif message['from'] == 'gpt' %}{{ '>>> Assistant: ' + message['value'] + eos_token + '\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '>>> Assistant: ' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|im_end|>",
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}