update tokenizer config

minilm_test.py

@@ -0,0 +1,10 @@
+from transformers import AutoTokenizer, AutoModel
+  
+tokenizer = AutoTokenizer.from_pretrained("BM-K/KoMiniLM-68M") # 23M model
+model = AutoModel.from_pretrained("BM-K/KoMiniLM-68M")
+
+inputs = tokenizer("안녕 세상아!", return_tensors="pt")
+outputs = model(**inputs)
+
+print(outputs)
+

tokenizer_config.json

@@ -1 +1 @@
-{"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": null, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/aeaaa3afd086a040be912f92ffe7b5f85008b744624f4517c4216bcc32b51cf0.054ece8d16bd524c8a00f0e8a976c00d5de22a755ffb79e353ee2954d9289e26", "name_or_path": "minilm_klue", "tokenizer_file": "minilm_klue/tokenizer.json", "tokenizer_class": "BertTokenizer"}
+{"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": null, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/aeaaa3afd086a040be912f92ffe7b5f85008b744624f4517c4216bcc32b51cf0.054ece8d16bd524c8a00f0e8a976c00d5de22a755ffb79e353ee2954d9289e26", "name_or_path": "minilm_klue", "tokenizer_class": "BertTokenizer"}