ar_colbert_5k_kd / tokenizer_config.json
akhooli's picture
Upload folder using huggingface_hub
1064873 verified
raw
history blame
2.17 kB
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[UNK]",
"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": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "[رابط]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true,
"special": true
},
"6": {
"content": "[بريد]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true,
"special": true
},
"7": {
"content": "[مستخدم]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true,
"special": true
},
"64000": {
"content": "[Q] ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"64001": {
"content": "[D] ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"max_len": 512,
"model_max_length": 512,
"never_split": [
"[بريد]",
"[مستخدم]",
"[رابط]"
],
"pad_token": "[MASK]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}