23 lines
688 B
JSON
23 lines
688 B
JSON
{
|
|
"bos_token": "<s>",
|
|
"cls_token": "<s>",
|
|
"eos_token": "</s>",
|
|
"full_tokenizer_file": null,
|
|
"mask_token": {
|
|
"__type": "AddedToken",
|
|
"content": "<mask>",
|
|
"lstrip": true,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false
|
|
},
|
|
"model_max_length": 512,
|
|
"name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-xlm-r-multilingual-v1/",
|
|
"pad_token": "<pad>",
|
|
"sep_token": "</s>",
|
|
"sp_model_kwargs": {},
|
|
"special_tokens_map_file": "input_models/johngiorgi-declutr-small-all-paraphrase-multilingual/0_Transformer/special_tokens_map.json",
|
|
"tokenizer_class": "XLMRobertaTokenizer",
|
|
"unk_token": "<unk>"
|
|
}
|