ET24_pangu_gpt2 / tokenizer_config.json
jiang-psy-infj's picture
Training in progress, step 2000
959e58f
raw
history blame contribute delete
877 Bytes
{
"add_bos_token": false,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "[BOS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "[EOS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"pad_token": {
"__type": "AddedToken",
"content": "[PAD]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sp_model_kwargs": {},
"tokenizer_class": "ChineseTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}