model improved

config.json

@@ -110,7 +110,7 @@
   "position_embedding_type": "absolute",
   "tokenizer_class": "BertTokenizerFast",
   "torch_dtype": "float32",
-  "transformers_version": "4.17.0",
+  "transformers_version": "4.40.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 2727

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd7c2d7b6bb2ee4fe03c5e02b3a40b8ca9291b154a8e3a4e8cdea201ce4b2bdb
-size 350398193
+oid sha256:fa24d980693c140dfcd4b6af6d9d141dda4179717af763b41f4d3cfb1151a535
+size 350381350

special_tokens_map.json

@@ -1 +1,37 @@
-{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

supar.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd110737980a43e86b7419d078aef75afc701f112f6be7de6cb5c0922db50ffe
-size 398882853
+oid sha256:ec080bc311cf685cecb798d95d6236e0edf14e636f57c7450e04f813d3b2aff4
+size 399082934

tokenizer_config.json

@@ -1 +1,67 @@
-{"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": false, "never_split": ["[CLS]", "[PAD]", "[SEP]", "[UNK]", "[MASK]"], "do_basic_tokenize": true, "model_max_length": 512, "tokenizer_class": "BertTokenizerFast"}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 510,
+  "model_max_length": 512,
+  "never_split": [
+    "[CLS]",
+    "[PAD]",
+    "[SEP]",
+    "[UNK]",
+    "[MASK]"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}