tigerbot-70b-base-v2 / tokenizer_config.json
i4never's picture
Update tokenizer_config.json
b77e1da
{
"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
},
"65107": {
"content": "\n\n### Instruction:\n",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"65108": {
"content": "\n\n### Response:\n",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"65109": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>",
"\n\n### Instruction:\n",
"\n\n### Response:\n",
"<pad>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true,
"add_bos_token": false,
"add_eos_token": false
}