ANHSY_0.1 / tokenizer_config.json
blueapple8259's picture
Upload 9 files
d3039c2
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"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
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"51200": {
"content": "###",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"51201": {
"content": "<끝>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"errors": "replace",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<unk>"
}