BPE-HF-CC100-FR / tokenizer_config.json
qanastek's picture
Upload 41 files
1764a0d
{
"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": 1000000000000000019884624838656,
"name_or_path": "./tokenizers/BpeTokenizer_CC100-FR_CHARS_lowercased_fixed_utf8-roberta/",
"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
},
"special_tokens_map_file": "./tokenizers/BpeTokenizer_CC100-FR_CHARS_lowercased_fixed_utf8-roberta/special_tokens_map.json",
"tokenizer_class": "RobertaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"use_fast": true
}