XLM_R_Galen-caresC / tokenizer_config.json
GuillemGSubies's picture
Upload the tokenizer
8fe7813
raw
history blame
615 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": "models/XLM_R_Galen-16-4e-05-0-caresC_best",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "models/XLM_R_Galen/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}