xlm-roberta-large-ehealth_kd / tokenizer_config.json
GuillemGSubies's picture
Upload the tokenizer
81874c9
raw
history blame
555 Bytes
{
"bos_token": "<s>",
"cls_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"keep_accents": true,
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_len": 512,
"model_max_length": 512,
"name_or_path": "xlm-roberta-large-16-2e-05-0.2-ehealth_kd_best",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": null,
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}