sysformbatches2acs / tokenizer_config.json
Ubuntu
Figured out labels issue
056f5c1
raw
history blame contribute delete
565 Bytes
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "/home/ubuntu/.cache/huggingface/transformers/b33bcac0ad2adc633578e3be3d1c37a843f13b95ed10144e41ce8e5619799226.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "./nxs62-patents-ner_SYSFORM_chembert_cased.model/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}