model improved

config.json

@@ -265,8 +265,7 @@
     "252": "VERB+PART",
     "253": "VERB+PUNCT",
     "254": "VERB+VERB",
-    "255": "X",
-    "256": "X+X"
+    "255": "X"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -526,8 +525,7 @@
     "VERB+PART": 252,
     "VERB+PUNCT": 253,
     "VERB+VERB": 254,
-    "X": 255,
-    "X+X": 256
+    "X": 255
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
@@ -1375,10 +1373,6 @@
         "\u0e42\u0e14\u0e22\u0e40\u0e2a\u0e23\u0e34\u0e21": [
           "\u0e42\u0e14\u0e22",
           "\u0e40\u0e2a\u0e23\u0e34\u0e21"
-        ],
-        "\u0e42\u0e14\u0e22\u0e40\u0e40\u0e1a\u0e48\u0e07": [
-          "\u0e42\u0e14\u0e22",
-          "\u0e40\u0e40\u0e1a\u0e48\u0e07"
         ]
       },
       "DET+DET": {
@@ -4814,10 +4808,6 @@
           "\u0e27\u0e38\u0e12\u0e34\u0e2a\u0e20\u0e32",
           "\u0e1e.\u0e28."
         ],
-        "\u0e2a\u0e38\u0e23\u0e2a\u0e31\u0e08\u0e08\u0e30": [
-          "\u0e2a\u0e38\u0e23\u0e2a\u0e31\u0e08\u0e08",
-          "\u0e30"
-        ],
         "\u0e2d.\u0e2d\u0e48\u0e32\u0e27\u0e25\u0e36\u0e01": [
           "\u0e2d.\u0e2d\u0e48\u0e32\u0e27\u0e25\u0e36",
           "\u0e01"
@@ -6352,10 +6342,6 @@
           "\u0e1a\u0e23\u0e34\u0e01\u0e32\u0e23",
           "\u0e40\u0e0a\u0e37\u0e49\u0e2d"
         ],
-        "\u0e1b\u0e23\u0e30\u0e08\u0e33\u0e17\u0e32\u0e07": [
-          "\u0e1b\u0e23\u0e30\u0e08",
-          "\u0e33\u0e17\u0e32\u0e07"
-        ],
         "\u0e1b\u0e23\u0e30\u0e0a\u0e38\u0e21\u0e19\u0e23\u0e32\u0e17\u0e31\u0e28\u0e19\u0e4c": [
           "\u0e1b\u0e23\u0e30\u0e0a\u0e38\u0e21",
           "\u0e19\u0e23\u0e32\u0e17\u0e31\u0e28\u0e19\u0e4c"
@@ -6852,10 +6838,6 @@
           "\u0e23\u0e31\u0e01\u0e29\u0e32\u0e01\u0e32\u0e23",
           "\u0e40\u0e09\u0e1e\u0e32\u0e30"
         ],
-        "\u0e23\u0e31\u0e1a\u0e1c\u0e34\u0e14\u0e0a\u0e2d\u0e1a": [
-          "\u0e23",
-          "\u0e31\u0e1a\u0e1c\u0e34\u0e14\u0e0a\u0e2d\u0e1a"
-        ],
         "\u0e23\u0e39\u0e49\u0e08\u0e31\u0e01\u0e23\u0e30\u0e21\u0e31\u0e14\u0e23\u0e30\u0e27\u0e31\u0e07": [
           "\u0e23\u0e39\u0e49\u0e08\u0e31\u0e01",
           "\u0e23\u0e30\u0e21\u0e31\u0e14\u0e23\u0e30\u0e27\u0e31\u0e07"
@@ -7062,17 +7044,13 @@
         "\u0e42\u0e19\u0e49\u0e15\u0e1a\u0e38\u0e4a\u0e04\u0e23\u0e38\u0e48\u0e19": [
           "\u0e42\u0e19\u0e49\u0e15\u0e1a\u0e38\u0e4a",
           "\u0e04\u0e23\u0e38\u0e48\u0e19"
-        ],
-        "\u0e42\u0e1b\u0e23": [
-          "\u0e42",
-          "\u0e1b\u0e23"
         ]
       }
     }
   },
   "tokenizer_class": "RemBertTokenizerFast",
   "torch_dtype": "float32",
-  "transformers_version": "4.17.0",
+  "transformers_version": "4.40.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 3005

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48514b6b9fe71bb22cacd7eb695a8290d03dc716f6bcc543c5a2bc000e08fc1
-size 351910513
+oid sha256:0fbc8c947cdf772a281a527db16a660817e9d0114ddfca69e39050de3e276b22
+size 351890598

special_tokens_map.json

@@ -1 +1,51 @@
-{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "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:ae1211c51189d32771825286722c249ed0c2ffda230686da8f406446eb05c551
-size 399759909
+oid sha256:2b27af124535b799117cc9fd151f54186c2a05a26db7cf5190e086164fcda807
+size 399959990

tokenizer.json

@@ -12167,6 +12167,7 @@
         "õ",
         -16.647894589647784
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1 +1,61 @@
-{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "tokenizer_class": "RemBertTokenizerFast"}
+{
+  "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": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "max_length": 510,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "RemBertTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}