cerbero-7b-openchat / tokenizer_config.json
galatolo's picture
Update tokenizer_config.json
1375be6 verified
{
"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": "<|end_of_turn|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|pad_0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|end_of_turn|>",
"<|pad_0|>"
],
"bos_token": "<s>",
"chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[|Umano|] ' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '[|Assistente|] ' + message['content'] + '\n' }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n' }}{% else %}{{ raise_exception('Only system, user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '[|Assistente|]' }}{% endif %}\n",
"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",
"trust_remote_code": false,
"unk_token": "<unk>",
"use_default_system_prompt": true,
"use_fast": true
}