pretrain_sent_concat / tokenizer_config.json
tingchih's picture
Upload tokenizer
c3ab595
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"cls_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 16384,
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"tokenizer_class": "LEDTokenizer",
"trim_offsets": true,
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}