model improved

config.json

@@ -5,7 +5,7 @@
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
-    "custom_pipelines": {
+  "custom_pipelines": {
     "upos": {
       "impl": "upos.BellmanFordTokenClassificationPipeline",
       "pt": "AutoModelForTokenClassification"
@@ -17,153 +17,105 @@
   "hidden_size": 768,
   "id2label": {
     "0": "ADJ",
-    "1": "ADP",
-    "2": "ADV",
-    "3": "AUX",
-    "4": "B-ADJ",
-    "5": "B-ADJ+ADP",
-    "6": "B-ADP",
+    "1": "B-ADJ",
+    "2": "I-ADJ",
+    "3": "ADP",
+    "4": "B-ADP",
+    "5": "I-ADP",
+    "6": "ADV",
     "7": "B-ADV",
-    "8": "B-AUX",
-    "9": "B-AUX+PART",
-    "10": "B-AUX+SCONJ",
-    "11": "B-DET",
-    "12": "B-INTJ",
-    "13": "B-NOUN",
-    "14": "B-NOUN+ADP",
-    "15": "B-NUM",
-    "16": "B-NUM+ADP",
-    "17": "B-PART",
-    "18": "B-PRON",
-    "19": "B-PRON+ADP",
-    "20": "B-PROPN",
-    "21": "B-PROPN+ADP",
-    "22": "B-PROPN+SCONJ",
-    "23": "B-PUNCT",
-    "24": "B-PUNCT+NOUN",
-    "25": "B-SCONJ",
-    "26": "B-VERB",
-    "27": "B-VERB+ADP",
-    "28": "B-VERB+PART",
-    "29": "B-VERB+SCONJ",
-    "30": "B-X",
-    "31": "DET",
-    "32": "I-ADJ",
-    "33": "I-ADJ+ADP",
-    "34": "I-ADP",
-    "35": "I-ADV",
-    "36": "I-AUX",
-    "37": "I-AUX+PART",
-    "38": "I-AUX+SCONJ",
-    "39": "I-DET",
-    "40": "I-INTJ",
-    "41": "I-NOUN",
-    "42": "I-NOUN+ADP",
-    "43": "I-NUM",
-    "44": "I-NUM+ADP",
-    "45": "I-PART",
-    "46": "I-PRON",
-    "47": "I-PRON+ADP",
-    "48": "I-PROPN",
-    "49": "I-PROPN+ADP",
-    "50": "I-PROPN+SCONJ",
-    "51": "I-PUNCT",
-    "52": "I-PUNCT+NOUN",
-    "53": "I-SCONJ",
-    "54": "I-VERB",
-    "55": "I-VERB+ADP",
-    "56": "I-VERB+PART",
-    "57": "I-VERB+SCONJ",
-    "58": "I-X",
-    "59": "INTJ",
-    "60": "NOUN",
-    "61": "NUM",
-    "62": "PART",
-    "63": "PART+NOUN",
-    "64": "PART+PUNCT",
-    "65": "PRON",
-    "66": "PROPN",
-    "67": "PUNCT",
-    "68": "SCONJ",
-    "69": "SYM",
-    "70": "VERB",
-    "71": "X"
+    "8": "I-ADV",
+    "9": "AUX",
+    "10": "B-AUX",
+    "11": "I-AUX",
+    "12": "DET",
+    "13": "B-DET",
+    "14": "I-DET",
+    "15": "INTJ",
+    "16": "B-INTJ",
+    "17": "I-INTJ",
+    "18": "NOUN",
+    "19": "B-NOUN",
+    "20": "I-NOUN",
+    "21": "NUM",
+    "22": "B-NUM",
+    "23": "I-NUM",
+    "24": "PART",
+    "25": "B-PART",
+    "26": "I-PART",
+    "27": "PRON",
+    "28": "B-PRON",
+    "29": "I-PRON",
+    "30": "PROPN",
+    "31": "B-PROPN",
+    "32": "I-PROPN",
+    "33": "PUNCT",
+    "34": "B-PUNCT",
+    "35": "I-PUNCT",
+    "36": "SCONJ",
+    "37": "B-SCONJ",
+    "38": "I-SCONJ",
+    "39": "SYM",
+    "40": "B-SYM",
+    "41": "I-SYM",
+    "42": "VERB",
+    "43": "B-VERB",
+    "44": "I-VERB",
+    "45": "X",
+    "46": "B-X",
+    "47": "I-X"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
     "ADJ": 0,
-    "ADP": 1,
-    "ADV": 2,
-    "AUX": 3,
-    "B-ADJ": 4,
-    "B-ADJ+ADP": 5,
-    "B-ADP": 6,
+    "ADP": 3,
+    "ADV": 6,
+    "AUX": 9,
+    "B-ADJ": 1,
+    "B-ADP": 4,
     "B-ADV": 7,
-    "B-AUX": 8,
-    "B-AUX+PART": 9,
-    "B-AUX+SCONJ": 10,
-    "B-DET": 11,
-    "B-INTJ": 12,
-    "B-NOUN": 13,
-    "B-NOUN+ADP": 14,
-    "B-NUM": 15,
-    "B-NUM+ADP": 16,
-    "B-PART": 17,
-    "B-PRON": 18,
-    "B-PRON+ADP": 19,
-    "B-PROPN": 20,
-    "B-PROPN+ADP": 21,
-    "B-PROPN+SCONJ": 22,
-    "B-PUNCT": 23,
-    "B-PUNCT+NOUN": 24,
-    "B-SCONJ": 25,
-    "B-VERB": 26,
-    "B-VERB+ADP": 27,
-    "B-VERB+PART": 28,
-    "B-VERB+SCONJ": 29,
-    "B-X": 30,
-    "DET": 31,
-    "I-ADJ": 32,
-    "I-ADJ+ADP": 33,
-    "I-ADP": 34,
-    "I-ADV": 35,
-    "I-AUX": 36,
-    "I-AUX+PART": 37,
-    "I-AUX+SCONJ": 38,
-    "I-DET": 39,
-    "I-INTJ": 40,
-    "I-NOUN": 41,
-    "I-NOUN+ADP": 42,
-    "I-NUM": 43,
-    "I-NUM+ADP": 44,
-    "I-PART": 45,
-    "I-PRON": 46,
-    "I-PRON+ADP": 47,
-    "I-PROPN": 48,
-    "I-PROPN+ADP": 49,
-    "I-PROPN+SCONJ": 50,
-    "I-PUNCT": 51,
-    "I-PUNCT+NOUN": 52,
-    "I-SCONJ": 53,
-    "I-VERB": 54,
-    "I-VERB+ADP": 55,
-    "I-VERB+PART": 56,
-    "I-VERB+SCONJ": 57,
-    "I-X": 58,
-    "INTJ": 59,
-    "NOUN": 60,
-    "NUM": 61,
-    "PART": 62,
-    "PART+NOUN": 63,
-    "PART+PUNCT": 64,
-    "PRON": 65,
-    "PROPN": 66,
-    "PUNCT": 67,
-    "SCONJ": 68,
-    "SYM": 69,
-    "VERB": 70,
-    "X": 71
+    "B-AUX": 10,
+    "B-DET": 13,
+    "B-INTJ": 16,
+    "B-NOUN": 19,
+    "B-NUM": 22,
+    "B-PART": 25,
+    "B-PRON": 28,
+    "B-PROPN": 31,
+    "B-PUNCT": 34,
+    "B-SCONJ": 37,
+    "B-SYM": 40,
+    "B-VERB": 43,
+    "B-X": 46,
+    "DET": 12,
+    "I-ADJ": 2,
+    "I-ADP": 5,
+    "I-ADV": 8,
+    "I-AUX": 11,
+    "I-DET": 14,
+    "I-INTJ": 17,
+    "I-NOUN": 20,
+    "I-NUM": 23,
+    "I-PART": 26,
+    "I-PRON": 29,
+    "I-PROPN": 32,
+    "I-PUNCT": 35,
+    "I-SCONJ": 38,
+    "I-SYM": 41,
+    "I-VERB": 44,
+    "I-X": 47,
+    "INTJ": 15,
+    "NOUN": 18,
+    "NUM": 21,
+    "PART": 24,
+    "PRON": 27,
+    "PROPN": 30,
+    "PUNCT": 33,
+    "SCONJ": 36,
+    "SYM": 39,
+    "VERB": 42,
+    "X": 45
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e6c8c1160a2a0d9e7169b2c28ee602c3718a47b35017112021016edadb2b1a
-size 366957990
+oid sha256:a2d68fd5c99236740af14cc943da0fc7016fda736216e3f1db10f3c504c0f527
+size 366884198