model improved

config.json

@@ -20,12 +20,15 @@
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
   "pooler_hidden_size": 1024,
-  "pos_att_type": null,
-  "position_biased_input": true,
-  "relative_attention": false,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
   "tokenizer_class": "DebertaV2TokenizerFast",
   "torch_dtype": "float32",
-  "transformers_version": "4.19.4",
+  "transformers_version": "4.22.1",
   "type_vocab_size": 0,
   "vocab_size": 32000
 }

deprel/config.json

@@ -5,7 +5,6 @@
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "eos_token_id": 2,
-  "finetuning_task": "pos",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
@@ -21,43 +20,45 @@
     "8": "B-compound",
     "9": "B-cop",
     "10": "B-csubj",
-    "11": "B-dep",
-    "12": "B-det",
-    "13": "B-discourse",
-    "14": "B-dislocated",
+    "11": "B-csubj:outer",
+    "12": "B-dep",
+    "13": "B-det",
+    "14": "B-discourse",
     "15": "B-fixed",
     "16": "B-mark",
     "17": "B-nmod",
     "18": "B-nsubj",
-    "19": "B-nummod",
-    "20": "B-obj",
-    "21": "B-obl",
-    "22": "B-punct",
-    "23": "B-root",
-    "24": "I-acl",
-    "25": "I-advcl",
-    "26": "I-advmod",
-    "27": "I-amod",
-    "28": "I-aux",
-    "29": "I-case",
-    "30": "I-cc",
-    "31": "I-ccomp",
-    "32": "I-compound",
-    "33": "I-cop",
-    "34": "I-csubj",
-    "35": "I-dep",
-    "36": "I-det",
-    "37": "I-discourse",
-    "38": "I-dislocated",
-    "39": "I-fixed",
-    "40": "I-mark",
-    "41": "I-nmod",
-    "42": "I-nsubj",
-    "43": "I-nummod",
-    "44": "I-obj",
-    "45": "I-obl",
-    "46": "I-punct",
-    "47": "I-root"
+    "19": "B-nsubj:outer",
+    "20": "B-nummod",
+    "21": "B-obj",
+    "22": "B-obl",
+    "23": "B-punct",
+    "24": "B-root",
+    "25": "I-acl",
+    "26": "I-advcl",
+    "27": "I-advmod",
+    "28": "I-amod",
+    "29": "I-aux",
+    "30": "I-case",
+    "31": "I-cc",
+    "32": "I-ccomp",
+    "33": "I-compound",
+    "34": "I-cop",
+    "35": "I-csubj",
+    "36": "I-csubj:outer",
+    "37": "I-dep",
+    "38": "I-det",
+    "39": "I-discourse",
+    "40": "I-fixed",
+    "41": "I-mark",
+    "42": "I-nmod",
+    "43": "I-nsubj",
+    "44": "I-nsubj:outer",
+    "45": "I-nummod",
+    "46": "I-obj",
+    "47": "I-obl",
+    "48": "I-punct",
+    "49": "I-root"
   },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
@@ -73,43 +74,45 @@
     "B-compound": 8,
     "B-cop": 9,
     "B-csubj": 10,
-    "B-dep": 11,
-    "B-det": 12,
-    "B-discourse": 13,
-    "B-dislocated": 14,
+    "B-csubj:outer": 11,
+    "B-dep": 12,
+    "B-det": 13,
+    "B-discourse": 14,
     "B-fixed": 15,
     "B-mark": 16,
     "B-nmod": 17,
     "B-nsubj": 18,
-    "B-nummod": 19,
-    "B-obj": 20,
-    "B-obl": 21,
-    "B-punct": 22,
-    "B-root": 23,
-    "I-acl": 24,
-    "I-advcl": 25,
-    "I-advmod": 26,
-    "I-amod": 27,
-    "I-aux": 28,
-    "I-case": 29,
-    "I-cc": 30,
-    "I-ccomp": 31,
-    "I-compound": 32,
-    "I-cop": 33,
-    "I-csubj": 34,
-    "I-dep": 35,
-    "I-det": 36,
-    "I-discourse": 37,
-    "I-dislocated": 38,
-    "I-fixed": 39,
-    "I-mark": 40,
-    "I-nmod": 41,
-    "I-nsubj": 42,
-    "I-nummod": 43,
-    "I-obj": 44,
-    "I-obl": 45,
-    "I-punct": 46,
-    "I-root": 47
+    "B-nsubj:outer": 19,
+    "B-nummod": 20,
+    "B-obj": 21,
+    "B-obl": 22,
+    "B-punct": 23,
+    "B-root": 24,
+    "I-acl": 25,
+    "I-advcl": 26,
+    "I-advmod": 27,
+    "I-amod": 28,
+    "I-aux": 29,
+    "I-case": 30,
+    "I-cc": 31,
+    "I-ccomp": 32,
+    "I-compound": 33,
+    "I-cop": 34,
+    "I-csubj": 35,
+    "I-csubj:outer": 36,
+    "I-dep": 37,
+    "I-det": 38,
+    "I-discourse": 39,
+    "I-fixed": 40,
+    "I-mark": 41,
+    "I-nmod": 42,
+    "I-nsubj": 43,
+    "I-nsubj:outer": 44,
+    "I-nummod": 45,
+    "I-obj": 46,
+    "I-obl": 47,
+    "I-punct": 48,
+    "I-root": 49
   },
   "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
@@ -121,12 +124,15 @@
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
   "pooler_hidden_size": 1024,
-  "pos_att_type": null,
-  "position_biased_input": true,
-  "relative_attention": false,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
   "tokenizer_class": "DebertaV2TokenizerFast",
   "torch_dtype": "float32",
-  "transformers_version": "4.19.4",
+  "transformers_version": "4.22.1",
   "type_vocab_size": 0,
   "vocab_size": 32000
 }

deprel/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2d5e996deaf7254efc9261b9abb01ffc068f0a12d217da7a2737364971b3b4
-size 1342748467
+oid sha256:559a6b3b5670fa1151f701d9b47155793669c10d487ac8c63bfa29a6d8baee87
+size 1546410675

deprel/special_tokens_map.json

@@ -1 +1,9 @@
-{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

deprel/tokenizer_config.json

@@ -1 +1,14 @@
-{"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"}
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": true,
+  "tokenizer_class": "DebertaV2TokenizerFast",
+  "unk_token": "[UNK]"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5953ef557ad39cdc7a2a7d83f820b72104e70d314d83f2d371f42d6003ec40d3
-size 1342559923
+oid sha256:0eb71213259b99844953acf8fb4a2ce8bcb0f88b172a5a78c5557cee487b973c
+size 1546213875

special_tokens_map.json

@@ -1 +1,9 @@
-{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tagger/config.json

@@ -5,7 +5,6 @@
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "eos_token_id": 2,
-  "finetuning_task": "pos",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
@@ -101,12 +100,15 @@
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
   "pooler_hidden_size": 1024,
-  "pos_att_type": null,
-  "position_biased_input": true,
-  "relative_attention": false,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
   "tokenizer_class": "DebertaV2TokenizerFast",
   "torch_dtype": "float32",
-  "transformers_version": "4.19.4",
+  "transformers_version": "4.22.1",
   "type_vocab_size": 0,
   "vocab_size": 32000
 }

tagger/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce99dd88b1df984c8969c5238679936bd9733ceb4111379e06d623c4e58175d
-size 1342707507
+oid sha256:bb18628c956c64104d2e34a55be4d94084b0305728ead8117bf31233ded6cd12
+size 1546361459

tagger/special_tokens_map.json

@@ -1 +1,9 @@
-{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tagger/tokenizer_config.json

@@ -1 +1,14 @@
-{"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"}
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": true,
+  "tokenizer_class": "DebertaV2TokenizerFast",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,14 @@
-{"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"}
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": true,
+  "tokenizer_class": "DebertaV2TokenizerFast",
+  "unk_token": "[UNK]"
+}