dataset_mentions / tokenizer_config.json
davanstrien's picture
davanstrien HF staff
Add model
40fd5e3
raw
history blame
1.5 kB
{
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"do_basic_tokenize": true,
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"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-mpnet-base-v2/",
"never_split": null,
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "MPNetTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}