Swallow-7b-plus-char-upos / tokenizer_config.json
KoichiYasuoka's picture
initial release
16eaf8a
raw
history blame
910 Bytes
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": "<s>",
"eos_token": "</s>",
"legacy": true,
"mask_token": "<unk>",
"model_max_length": 4096,
"pad_token": "</s>",
"sep_token": "<s>",
"tokenizer_class": "LlamaTokenizerFast",
"unk_token": "<unk>",
"use_default_system_prompt": false
}