eubert_embedding_v1 / tokenizer_config.json
scampion's picture
Upload tokenizer
36c93d2
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[MASK]",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65536": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65537": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65538": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65539": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65540": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"[UNK]",
"[PAD]",
"[CLS]",
"[SEP]",
"[MASK]",
"<s>",
"</s>",
"<unk>",
"<pad>",
"<mask>"
],
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"eos_token": "[SEP]",
"errors": "replace",
"mask_token": "[MASK]",
"max_len": 512,
"max_length": 75,
"model_max_length": 512,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}