funnel-test / tokenizer_config.json
lectura's picture
Training in progress, epoch 1
3f22f26
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"96": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"97": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<cls>",
"do_basic_tokenize": true,
"do_lower_case": true,
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 512,
"never_split": null,
"pad_token": "<pad>",
"sep_token": "<sep>",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "FunnelTokenizer",
"unk_token": "<unk>"
}