model improved

config.json

@@ -261,8 +261,7 @@
     "251": "VERB+PART",
     "252": "VERB+PUNCT",
     "253": "VERB+VERB",
-    "254": "X",
-    "255": "X+X"
+    "254": "X"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -521,8 +520,7 @@
     "VERB+PART": 251,
     "VERB+PUNCT": 252,
     "VERB+VERB": 253,
-    "X": 254,
-    "X+X": 255
+    "X": 254
   },
   "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
@@ -1384,10 +1382,6 @@
         "\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": {
@@ -4847,10 +4841,6 @@
           "\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"
@@ -6407,10 +6397,6 @@
           "\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"
@@ -6903,10 +6889,6 @@
           "\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"
@@ -7113,17 +7095,13 @@
         "\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": "DebertaV2TokenizerFast",
   "torch_dtype": "float32",
-  "transformers_version": "4.19.2",
+  "transformers_version": "4.40.1",
   "type_vocab_size": 0,
   "vocab_size": 3000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4df0a015f13d3d01f865929497bed7bc19ebceb23cba209343750ccda3dafb
-size 351871347
+oid sha256:6affcb1836a4840990d2062d60cc3a128e3227d36e1246ad54ab40fc5f0940cf
+size 351866018

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": "[MASK]"}
+{
+  "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": 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:c4bba8e755ff6cfa5ac3dcfd17e1d95b7c9228186a1141ff7c8afc592f5d73a9
-size 397593643
+oid sha256:d2776e81c062b841d36b9d422a1ddfd32c79f82659afeed9912f7864ba4cc0c4
+size 397575682

tokenizer.json

@@ -12156,6 +12156,7 @@
         "ü",
         -16.64917507077761
       ]
-    ]
+    ],
+    "byte_fallback": false
   }
 }

tokenizer_config.json

@@ -1 +1,61 @@
-{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": true, "keep_accents": true, "model_max_length": 512, "tokenizer_class": "DebertaV2TokenizerFast"}
+{
+  "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
+    }
+  },
+  "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]",
+  "sep_token": "[SEP]",
+  "split_by_punct": true,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2TokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}