multiconer1_kb_muril / tokenizer_config.json
sumitrsch's picture
Upload 4 files
a689ecf verified
raw
history blame contribute delete
547 Bytes
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "lowercase": false, "special_tokens_map_file": "/home/naive123/.cache/huggingface/transformers/fe115eb36e01f7ae03038ded522b3340928096d8387073f9347ff97b2bd201f2.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "google/muril-large-cased", "tokenizer_class": "BertTokenizer"}