xlm-roberta-base-ance-en-jp-warmup / tokenizer_config.json
k-ush's picture
Initial commit
b8d2f46
raw
history blame contribute delete
683 Bytes
{
"bos_token": "<s>",
"cls_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"max_len": 512,
"model_max_length": 512,
"name_or_path": "../model/xlm/checkpoint-30000",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "/home/kush/.cache/huggingface/hub/models--k-ush--xlm-roberta-base-ance-warmup/snapshots/2a379ede296696aabd5fb92b5f9b7fa2705a532f/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}