add tokenizer

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 384,
     "strategy": "OnlySecond",
     "stride": 128
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 384
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/storage/mrm8488/biomedtra-small-es/checkpoint-7252", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/storage/mrm8488/checkpoint-82960/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}