PatentSBERTa_V2 / tokenizer_config.json
HamidBekam's picture
New version (V2) PatentSBERTa
4077104
raw
history blame
552 Bytes
{"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/home/ubuntu/storage_data_new/data_strato_old/deeppatentsimilarity/python_screen/patent_multi_classification/output/training_stsbenchmark_flax-sentence-embeddings-all_datasets_v3_mpnet-base-2022-05-15_01-34-49", "tokenizer_class": "MPNetTokenizer"}