model improved

maker.py

@@ -41,8 +41,8 @@ class UDgoeswithDataset(object):
     return lid
   __len__=lambda self:len(self.ids)
   __getitem__=lambda self,i:{"input_ids":self.ids[i],"labels":[self.label2id[t] for t in self.tags[i]]}
-from transformers import BertTokenizer,AutoConfig,AutoModelForTokenClassification,DataCollatorForTokenClassification,TrainingArguments,Trainer
-tkz=BertTokenizer.from_pretrained(src,do_lower_case=False,strip_accents=False,model_max_length=512)
+from transformers import AutoTokenizer,AutoConfig,AutoModelForTokenClassification,DataCollatorForTokenClassification,TrainingArguments,Trainer
+tkz=AutoTokenizer.from_pretrained(src)
 trainDS=UDgoeswithDataset("train.conllu",tkz)
 devDS=UDgoeswithDataset("dev.conllu",tkz)
 testDS=UDgoeswithDataset("test.conllu",tkz)

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207ec4f0beeea3b44bfb1648383559364a6f5458aff6335778b5a909536f8ddd
+oid sha256:53a888fb108192c80f8a0e937ca661808334b94961eee95832a70f7181b8e93c
 size 441306865

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": false,
+  "do_lower_case": true,
   "do_lowercase": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,