initial release

README.md

@@ -0,0 +1,30 @@
+---
+language:
+- "th"
+tags:
+- "thai"
+- "pos"
+- "dependency-parsing"
+base_model: meta-llama/Llama-3.2-1B
+datasets:
+- "universal_dependencies"
+license: "apache-2.0"
+pipeline_tag: "token-classification"
+widget:
+- text: "หลายหัวดีกว่าหัวเดียว"
+---
+
+# Llama-3.2-1B-thai-ud-causal
+
+## Model Description
+
+This is a LLaMA model pre-trained for POS-tagging and dependency-parsing, derived from [Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) refined for [Thai Universal Dependency Treebank](https://github.com/nlp-chula/TUD).
+
+## How to Use
+
+```py
+from transformers import pipeline
+nlp=pipeline("universal-dependencies","KoichiYasuoka/Llama-3.2-1B-thai-ud-causal",trust_remote_code=True)
+print(nlp("หลายหัวดีกว่าหัวเดียว"))
+```
+

config.json

@@ -0,0 +1,2076 @@
+{
+  "architectures": [
+    "LlamaForTokenClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "custom_pipelines": {
+    "upos": {
+      "impl": "ud.BellmanFordTokenClassificationPipeline",
+      "pt": "AutoModelForTokenClassification"
+    },
+    "universal-dependencies": {
+      "impl": "ud.UniversalDependenciesCausalPipeline",
+      "pt": "AutoModelForTokenClassification"
+    }
+  },
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "ADP",
+    "1": "ADP|Foreign=Yes",
+    "2": "ADP|Foreign=Yes|l-case",
+    "3": "ADP|NounType=Class",
+    "4": "ADP|NounType=Class|l-case",
+    "5": "ADP|Prefix=Yes",
+    "6": "ADP|Prefix=Yes|l-case",
+    "7": "ADP|Prefix=Yes|l-mark",
+    "8": "ADP|l-acl",
+    "9": "ADP|l-advcl",
+    "10": "ADP|l-advmod",
+    "11": "ADP|l-case",
+    "12": "ADP|l-cc",
+    "13": "ADP|l-dep",
+    "14": "ADP|l-fixed",
+    "15": "ADP|l-flat",
+    "16": "ADP|l-mark",
+    "17": "ADP|l-nmod",
+    "18": "ADP|l-nsubj",
+    "19": "ADP|l-obl",
+    "20": "ADP|l-orphan",
+    "21": "ADP|r-acl",
+    "22": "ADP|r-advmod",
+    "23": "ADP|r-case",
+    "24": "ADP|r-compound",
+    "25": "ADP|r-conj",
+    "26": "ADP|r-fixed",
+    "27": "ADP|r-flat",
+    "28": "ADP|r-obl",
+    "29": "ADP|r-orphan",
+    "30": "ADP|root",
+    "31": "ADV",
+    "32": "ADV|Foreign=Yes",
+    "33": "ADV|Foreign=Yes|l-advmod",
+    "34": "ADV|Foreign=Yes|r-advmod",
+    "35": "ADV|NumType=Mult",
+    "36": "ADV|NumType=Mult|r-advmod",
+    "37": "ADV|PartType=Adv",
+    "38": "ADV|PartType=Adv|l-advmod",
+    "39": "ADV|PartType=Adv|l-mark",
+    "40": "ADV|PartType=Adv|r-advmod",
+    "41": "ADV|PartType=Enp",
+    "42": "ADV|PartType=Enp|l-advmod",
+    "43": "ADV|PartType=Enp|r-advmod",
+    "44": "ADV|PartType=Int",
+    "45": "ADV|PartType=Int|r-advmod",
+    "46": "ADV|PartType=Int|r-fixed",
+    "47": "ADV|Prefix=Yes",
+    "48": "ADV|Prefix=Yes|l-advmod",
+    "49": "ADV|Prefix=Yes|l-mark",
+    "50": "ADV|Prefix=Yes|r-advmod",
+    "51": "ADV|l-acl",
+    "52": "ADV|l-advcl",
+    "53": "ADV|l-advmod",
+    "54": "ADV|l-aux",
+    "55": "ADV|l-case",
+    "56": "ADV|l-compound",
+    "57": "ADV|l-dep",
+    "58": "ADV|l-det",
+    "59": "ADV|l-discourse",
+    "60": "ADV|l-fixed",
+    "61": "ADV|l-mark",
+    "62": "ADV|l-orphan",
+    "63": "ADV|r-acl",
+    "64": "ADV|r-advcl",
+    "65": "ADV|r-advmod",
+    "66": "ADV|r-aux",
+    "67": "ADV|r-compound",
+    "68": "ADV|r-conj",
+    "69": "ADV|r-det",
+    "70": "ADV|r-fixed",
+    "71": "ADV|r-flat",
+    "72": "ADV|r-mark",
+    "73": "ADV|r-nmod",
+    "74": "ADV|r-obj",
+    "75": "ADV|r-orphan",
+    "76": "ADV|r-xcomp",
+    "77": "ADV|root",
+    "78": "AUX",
+    "79": "AUX|Foreign=Yes",
+    "80": "AUX|Foreign=Yes|l-aux",
+    "81": "AUX|NounType=Class",
+    "82": "AUX|NounType=Class|r-appos",
+    "83": "AUX|Prefix=Yes",
+    "84": "AUX|Prefix=Yes|l-aux",
+    "85": "AUX|Prefix=Yes|r-aux",
+    "86": "AUX|VerbType=Cop",
+    "87": "AUX|VerbType=Cop|l-acl",
+    "88": "AUX|VerbType=Cop|l-advcl",
+    "89": "AUX|VerbType=Cop|l-aux",
+    "90": "AUX|VerbType=Cop|l-cop",
+    "91": "AUX|VerbType=Cop|r-acl",
+    "92": "AUX|VerbType=Cop|r-advcl",
+    "93": "AUX|VerbType=Cop|r-aux",
+    "94": "AUX|VerbType=Cop|r-conj",
+    "95": "AUX|VerbType=Cop|r-mark",
+    "96": "AUX|VerbType=Cop|root",
+    "97": "AUX|l-advmod",
+    "98": "AUX|l-aux",
+    "99": "AUX|l-cop",
+    "100": "AUX|l-mark",
+    "101": "AUX|r-acl",
+    "102": "AUX|r-advmod",
+    "103": "AUX|r-aux",
+    "104": "AUX|r-ccomp",
+    "105": "AUX|r-clf",
+    "106": "AUX|r-compound",
+    "107": "AUX|r-conj",
+    "108": "AUX|r-fixed",
+    "109": "AUX|root",
+    "110": "B-ADP",
+    "111": "B-ADP|Foreign=Yes",
+    "112": "B-ADP|NounType=Class",
+    "113": "B-ADP|Prefix=Yes",
+    "114": "B-ADV",
+    "115": "B-ADV|Foreign=Yes",
+    "116": "B-ADV|NumType=Mult",
+    "117": "B-ADV|PartType=Adv",
+    "118": "B-ADV|PartType=Enp",
+    "119": "B-ADV|PartType=Int",
+    "120": "B-ADV|Prefix=Yes",
+    "121": "B-AUX",
+    "122": "B-AUX|Foreign=Yes",
+    "123": "B-AUX|NounType=Class",
+    "124": "B-AUX|Prefix=Yes",
+    "125": "B-AUX|VerbType=Cop",
+    "126": "B-CCONJ",
+    "127": "B-CCONJ|Foreign=Yes",
+    "128": "B-CCONJ|PronType=Prs",
+    "129": "B-DET",
+    "130": "B-DET|NumType=Mult",
+    "131": "B-DET|PartType=Emp",
+    "132": "B-DET|PartType=Int",
+    "133": "B-NOUN",
+    "134": "B-NOUN|Abbr=Yes",
+    "135": "B-NOUN|Abbr=Yes|Foreign=Yes",
+    "136": "B-NOUN|Abbr=Yes|Prefix=Yes",
+    "137": "B-NOUN|Foreign=Yes",
+    "138": "B-NOUN|Foreign=Yes|NounType=Class",
+    "139": "B-NOUN|Foreign=Yes|Prefix=Yes",
+    "140": "B-NOUN|NameType=Com",
+    "141": "B-NOUN|NameType=Geo",
+    "142": "B-NOUN|NameType=Nat",
+    "143": "B-NOUN|NameType=Oth",
+    "144": "B-NOUN|NameType=Pro",
+    "145": "B-NOUN|NameType=Prs",
+    "146": "B-NOUN|NounType=Class",
+    "147": "B-NOUN|NounType=Class|Prefix=Yes",
+    "148": "B-NOUN|NumType=Mult",
+    "149": "B-NOUN|PartType=Enp",
+    "150": "B-NOUN|PartType=Int",
+    "151": "B-NOUN|PartType=Res",
+    "152": "B-NOUN|Prefix=Yes",
+    "153": "B-NUM",
+    "154": "B-NUM|Abbr=Yes",
+    "155": "B-NUM|Foreign=Yes",
+    "156": "B-NUM|NumType=Mult",
+    "157": "B-NUM|Prefix=Yes",
+    "158": "B-PART",
+    "159": "B-PART|NameType=Oth",
+    "160": "B-PART|NounType=Class|PartType=Emp",
+    "161": "B-PART|NounType=Class|PartType=Emp|Prefix=Yes",
+    "162": "B-PART|NounType=Class|Prefix=Yes",
+    "163": "B-PART|NumType=Mult|PartType=Emp",
+    "164": "B-PART|PartType=Adj",
+    "165": "B-PART|PartType=Adv",
+    "166": "B-PART|PartType=Emp",
+    "167": "B-PART|PartType=Emp|Prefix=Yes",
+    "168": "B-PART|PartType=Enp",
+    "169": "B-PART|PartType=Int",
+    "170": "B-PART|PartType=Neg",
+    "171": "B-PART|PartType=Res",
+    "172": "B-PART|Prefix=Yes",
+    "173": "B-PRON",
+    "174": "B-PRON|NounType=Class",
+    "175": "B-PRON|PronType=Prs",
+    "176": "B-PRON|PronType=Rcp",
+    "177": "B-PROPN",
+    "178": "B-PROPN|Abbr=Yes",
+    "179": "B-PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth",
+    "180": "B-PROPN|Abbr=Yes|NameType=Com",
+    "181": "B-PROPN|Foreign=Yes",
+    "182": "B-PROPN|Foreign=Yes|NameType=Com",
+    "183": "B-PROPN|Foreign=Yes|NameType=Geo",
+    "184": "B-PROPN|Foreign=Yes|NameType=Giv",
+    "185": "B-PROPN|Foreign=Yes|NameType=Oth",
+    "186": "B-PROPN|Foreign=Yes|NameType=Prs",
+    "187": "B-PROPN|Foreign=Yes|NameType=Sur",
+    "188": "B-PROPN|NameType=Com",
+    "189": "B-PROPN|NameType=Geo",
+    "190": "B-PROPN|NameType=Giv",
+    "191": "B-PROPN|NameType=Nat",
+    "192": "B-PROPN|NameType=Oth",
+    "193": "B-PROPN|NameType=Pro",
+    "194": "B-PROPN|NameType=Prs",
+    "195": "B-PROPN|NameType=Sur",
+    "196": "B-PROPN|NounType=Class",
+    "197": "B-PROPN|Prefix=Yes",
+    "198": "B-PUNCT",
+    "199": "B-PUNCT|NounType=Class",
+    "200": "B-SCONJ",
+    "201": "B-SCONJ|NumType=Mult",
+    "202": "B-SCONJ|Prefix=Yes",
+    "203": "B-SCONJ|VerbType=Cop",
+    "204": "B-SYM",
+    "205": "B-VERB",
+    "206": "B-VERB|Abbr=Yes",
+    "207": "B-VERB|Foreign=Yes",
+    "208": "B-VERB|NounType=Class",
+    "209": "B-VERB|PartType=Adj",
+    "210": "B-VERB|Prefix=Yes",
+    "211": "B-VERB|VerbType=Cop",
+    "212": "CCONJ",
+    "213": "CCONJ|Foreign=Yes",
+    "214": "CCONJ|Foreign=Yes|l-cc",
+    "215": "CCONJ|PronType=Prs",
+    "216": "CCONJ|PronType=Prs|l-cc",
+    "217": "CCONJ|l-advmod",
+    "218": "CCONJ|l-case",
+    "219": "CCONJ|l-cc",
+    "220": "CCONJ|l-conj",
+    "221": "CCONJ|l-discourse",
+    "222": "CCONJ|l-fixed",
+    "223": "CCONJ|l-flat",
+    "224": "CCONJ|l-mark",
+    "225": "CCONJ|l-nsubj",
+    "226": "CCONJ|l-obj",
+    "227": "CCONJ|l-orphan",
+    "228": "CCONJ|r-cc",
+    "229": "CCONJ|r-compound",
+    "230": "CCONJ|r-fixed",
+    "231": "CCONJ|r-mark",
+    "232": "DET",
+    "233": "DET|NumType=Mult",
+    "234": "DET|NumType=Mult|l-det",
+    "235": "DET|PartType=Emp",
+    "236": "DET|PartType=Emp|r-det",
+    "237": "DET|PartType=Int",
+    "238": "DET|PartType=Int|r-det",
+    "239": "DET|l-compound",
+    "240": "DET|l-det",
+    "241": "DET|l-discourse",
+    "242": "DET|l-nsubj",
+    "243": "DET|l-obl",
+    "244": "DET|l-orphan",
+    "245": "DET|r-advmod",
+    "246": "DET|r-compound",
+    "247": "DET|r-conj",
+    "248": "DET|r-dep",
+    "249": "DET|r-det",
+    "250": "DET|r-fixed",
+    "251": "DET|r-flat",
+    "252": "DET|r-list",
+    "253": "DET|r-nmod",
+    "254": "DET|r-nummod",
+    "255": "DET|r-obl",
+    "256": "DET|r-orphan",
+    "257": "I-ADP",
+    "258": "I-ADP|Foreign=Yes",
+    "259": "I-ADP|NounType=Class",
+    "260": "I-ADP|Prefix=Yes",
+    "261": "I-ADV",
+    "262": "I-ADV|Foreign=Yes",
+    "263": "I-ADV|NumType=Mult",
+    "264": "I-ADV|PartType=Adv",
+    "265": "I-ADV|PartType=Enp",
+    "266": "I-ADV|PartType=Int",
+    "267": "I-ADV|Prefix=Yes",
+    "268": "I-AUX",
+    "269": "I-AUX|Foreign=Yes",
+    "270": "I-AUX|NounType=Class",
+    "271": "I-AUX|Prefix=Yes",
+    "272": "I-AUX|VerbType=Cop",
+    "273": "I-CCONJ",
+    "274": "I-CCONJ|Foreign=Yes",
+    "275": "I-CCONJ|PronType=Prs",
+    "276": "I-DET",
+    "277": "I-DET|NumType=Mult",
+    "278": "I-DET|PartType=Emp",
+    "279": "I-DET|PartType=Int",
+    "280": "I-NOUN",
+    "281": "I-NOUN|Abbr=Yes",
+    "282": "I-NOUN|Abbr=Yes|Foreign=Yes",
+    "283": "I-NOUN|Abbr=Yes|Prefix=Yes",
+    "284": "I-NOUN|Foreign=Yes",
+    "285": "I-NOUN|Foreign=Yes|NounType=Class",
+    "286": "I-NOUN|Foreign=Yes|Prefix=Yes",
+    "287": "I-NOUN|NameType=Com",
+    "288": "I-NOUN|NameType=Geo",
+    "289": "I-NOUN|NameType=Nat",
+    "290": "I-NOUN|NameType=Oth",
+    "291": "I-NOUN|NameType=Pro",
+    "292": "I-NOUN|NameType=Prs",
+    "293": "I-NOUN|NounType=Class",
+    "294": "I-NOUN|NounType=Class|Prefix=Yes",
+    "295": "I-NOUN|NumType=Mult",
+    "296": "I-NOUN|PartType=Enp",
+    "297": "I-NOUN|PartType=Int",
+    "298": "I-NOUN|PartType=Res",
+    "299": "I-NOUN|Prefix=Yes",
+    "300": "I-NUM",
+    "301": "I-NUM|Abbr=Yes",
+    "302": "I-NUM|Foreign=Yes",
+    "303": "I-NUM|NumType=Mult",
+    "304": "I-NUM|Prefix=Yes",
+    "305": "I-PART",
+    "306": "I-PART|NameType=Oth",
+    "307": "I-PART|NounType=Class|PartType=Emp",
+    "308": "I-PART|NounType=Class|PartType=Emp|Prefix=Yes",
+    "309": "I-PART|NounType=Class|Prefix=Yes",
+    "310": "I-PART|NumType=Mult|PartType=Emp",
+    "311": "I-PART|PartType=Adj",
+    "312": "I-PART|PartType=Adv",
+    "313": "I-PART|PartType=Emp",
+    "314": "I-PART|PartType=Emp|Prefix=Yes",
+    "315": "I-PART|PartType=Enp",
+    "316": "I-PART|PartType=Int",
+    "317": "I-PART|PartType=Neg",
+    "318": "I-PART|PartType=Res",
+    "319": "I-PART|Prefix=Yes",
+    "320": "I-PRON",
+    "321": "I-PRON|NounType=Class",
+    "322": "I-PRON|PronType=Prs",
+    "323": "I-PRON|PronType=Rcp",
+    "324": "I-PROPN",
+    "325": "I-PROPN|Abbr=Yes",
+    "326": "I-PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth",
+    "327": "I-PROPN|Abbr=Yes|NameType=Com",
+    "328": "I-PROPN|Foreign=Yes",
+    "329": "I-PROPN|Foreign=Yes|NameType=Com",
+    "330": "I-PROPN|Foreign=Yes|NameType=Geo",
+    "331": "I-PROPN|Foreign=Yes|NameType=Giv",
+    "332": "I-PROPN|Foreign=Yes|NameType=Oth",
+    "333": "I-PROPN|Foreign=Yes|NameType=Prs",
+    "334": "I-PROPN|Foreign=Yes|NameType=Sur",
+    "335": "I-PROPN|NameType=Com",
+    "336": "I-PROPN|NameType=Geo",
+    "337": "I-PROPN|NameType=Giv",
+    "338": "I-PROPN|NameType=Nat",
+    "339": "I-PROPN|NameType=Oth",
+    "340": "I-PROPN|NameType=Pro",
+    "341": "I-PROPN|NameType=Prs",
+    "342": "I-PROPN|NameType=Sur",
+    "343": "I-PROPN|NounType=Class",
+    "344": "I-PROPN|Prefix=Yes",
+    "345": "I-PUNCT",
+    "346": "I-PUNCT|NounType=Class",
+    "347": "I-SCONJ",
+    "348": "I-SCONJ|NumType=Mult",
+    "349": "I-SCONJ|Prefix=Yes",
+    "350": "I-SCONJ|VerbType=Cop",
+    "351": "I-SYM",
+    "352": "I-VERB",
+    "353": "I-VERB|Abbr=Yes",
+    "354": "I-VERB|Foreign=Yes",
+    "355": "I-VERB|NounType=Class",
+    "356": "I-VERB|PartType=Adj",
+    "357": "I-VERB|Prefix=Yes",
+    "358": "I-VERB|VerbType=Cop",
+    "359": "NOUN",
+    "360": "NOUN|Abbr=Yes",
+    "361": "NOUN|Abbr=Yes|Foreign=Yes",
+    "362": "NOUN|Abbr=Yes|Foreign=Yes|r-nmod",
+    "363": "NOUN|Abbr=Yes|Prefix=Yes",
+    "364": "NOUN|Abbr=Yes|Prefix=Yes|l-flat",
+    "365": "NOUN|Abbr=Yes|l-flat",
+    "366": "NOUN|Abbr=Yes|l-nmod",
+    "367": "NOUN|Abbr=Yes|l-nsubj",
+    "368": "NOUN|Abbr=Yes|l-obl",
+    "369": "NOUN|Abbr=Yes|r-acl",
+    "370": "NOUN|Abbr=Yes|r-appos",
+    "371": "NOUN|Abbr=Yes|r-clf",
+    "372": "NOUN|Abbr=Yes|r-conj",
+    "373": "NOUN|Abbr=Yes|r-fixed",
+    "374": "NOUN|Abbr=Yes|r-flat",
+    "375": "NOUN|Abbr=Yes|r-nmod",
+    "376": "NOUN|Abbr=Yes|r-obj",
+    "377": "NOUN|Abbr=Yes|r-obl",
+    "378": "NOUN|Foreign=Yes",
+    "379": "NOUN|Foreign=Yes|NounType=Class",
+    "380": "NOUN|Foreign=Yes|NounType=Class|r-clf",
+    "381": "NOUN|Foreign=Yes|NounType=Class|r-obj",
+    "382": "NOUN|Foreign=Yes|Prefix=Yes",
+    "383": "NOUN|Foreign=Yes|Prefix=Yes|l-flat",
+    "384": "NOUN|Foreign=Yes|Prefix=Yes|r-appos",
+    "385": "NOUN|Foreign=Yes|l-dislocated",
+    "386": "NOUN|Foreign=Yes|l-flat",
+    "387": "NOUN|Foreign=Yes|l-nmod",
+    "388": "NOUN|Foreign=Yes|l-nsubj",
+    "389": "NOUN|Foreign=Yes|l-obl",
+    "390": "NOUN|Foreign=Yes|r-acl",
+    "391": "NOUN|Foreign=Yes|r-advcl",
+    "392": "NOUN|Foreign=Yes|r-advmod",
+    "393": "NOUN|Foreign=Yes|r-appos",
+    "394": "NOUN|Foreign=Yes|r-ccomp",
+    "395": "NOUN|Foreign=Yes|r-clf",
+    "396": "NOUN|Foreign=Yes|r-compound",
+    "397": "NOUN|Foreign=Yes|r-conj",
+    "398": "NOUN|Foreign=Yes|r-flat",
+    "399": "NOUN|Foreign=Yes|r-iobj",
+    "400": "NOUN|Foreign=Yes|r-list",
+    "401": "NOUN|Foreign=Yes|r-nmod",
+    "402": "NOUN|Foreign=Yes|r-obj",
+    "403": "NOUN|Foreign=Yes|r-obl",
+    "404": "NOUN|Foreign=Yes|r-xcomp",
+    "405": "NOUN|Foreign=Yes|root",
+    "406": "NOUN|NameType=Com",
+    "407": "NOUN|NameType=Com|r-nmod",
+    "408": "NOUN|NameType=Geo",
+    "409": "NOUN|NameType=Geo|l-nsubj",
+    "410": "NOUN|NameType=Geo|r-nmod",
+    "411": "NOUN|NameType=Geo|r-obj",
+    "412": "NOUN|NameType=Nat",
+    "413": "NOUN|NameType=Nat|r-nmod",
+    "414": "NOUN|NameType=Oth",
+    "415": "NOUN|NameType=Oth|l-nsubj",
+    "416": "NOUN|NameType=Oth|r-conj",
+    "417": "NOUN|NameType=Oth|r-flat",
+    "418": "NOUN|NameType=Oth|r-nmod",
+    "419": "NOUN|NameType=Pro",
+    "420": "NOUN|NameType=Pro|r-nmod",
+    "421": "NOUN|NameType=Prs",
+    "422": "NOUN|NameType=Prs|l-nsubj",
+    "423": "NOUN|NameType=Prs|r-nmod",
+    "424": "NOUN|NounType=Class",
+    "425": "NOUN|NounType=Class|Prefix=Yes",
+    "426": "NOUN|NounType=Class|Prefix=Yes|l-advcl",
+    "427": "NOUN|NounType=Class|Prefix=Yes|l-advmod",
+    "428": "NOUN|NounType=Class|Prefix=Yes|l-mark",
+    "429": "NOUN|NounType=Class|Prefix=Yes|l-nmod",
+    "430": "NOUN|NounType=Class|Prefix=Yes|l-nsubj",
+    "431": "NOUN|NounType=Class|Prefix=Yes|r-advcl",
+    "432": "NOUN|NounType=Class|Prefix=Yes|r-clf",
+    "433": "NOUN|NounType=Class|Prefix=Yes|r-nmod",
+    "434": "NOUN|NounType=Class|Prefix=Yes|r-obj",
+    "435": "NOUN|NounType=Class|l-advcl",
+    "436": "NOUN|NounType=Class|l-advmod",
+    "437": "NOUN|NounType=Class|l-clf",
+    "438": "NOUN|NounType=Class|l-dislocated",
+    "439": "NOUN|NounType=Class|l-nmod",
+    "440": "NOUN|NounType=Class|l-nsubj",
+    "441": "NOUN|NounType=Class|l-obj",
+    "442": "NOUN|NounType=Class|l-obl",
+    "443": "NOUN|NounType=Class|r-acl",
+    "444": "NOUN|NounType=Class|r-advcl",
+    "445": "NOUN|NounType=Class|r-advmod",
+    "446": "NOUN|NounType=Class|r-appos",
+    "447": "NOUN|NounType=Class|r-cc",
+    "448": "NOUN|NounType=Class|r-ccomp",
+    "449": "NOUN|NounType=Class|r-clf",
+    "450": "NOUN|NounType=Class|r-compound",
+    "451": "NOUN|NounType=Class|r-conj",
+    "452": "NOUN|NounType=Class|r-dislocated",
+    "453": "NOUN|NounType=Class|r-fixed",
+    "454": "NOUN|NounType=Class|r-flat",
+    "455": "NOUN|NounType=Class|r-iobj",
+    "456": "NOUN|NounType=Class|r-list",
+    "457": "NOUN|NounType=Class|r-nmod",
+    "458": "NOUN|NounType=Class|r-nummod",
+    "459": "NOUN|NounType=Class|r-obj",
+    "460": "NOUN|NounType=Class|r-obl",
+    "461": "NOUN|NounType=Class|r-orphan",
+    "462": "NOUN|NounType=Class|r-xcomp",
+    "463": "NOUN|NounType=Class|root",
+    "464": "NOUN|NumType=Mult",
+    "465": "NOUN|NumType=Mult|r-advcl",
+    "466": "NOUN|NumType=Mult|r-nmod",
+    "467": "NOUN|NumType=Mult|r-obj",
+    "468": "NOUN|PartType=Enp",
+    "469": "NOUN|PartType=Enp|r-obj",
+    "470": "NOUN|PartType=Enp|r-obl",
+    "471": "NOUN|PartType=Int",
+    "472": "NOUN|PartType=Int|r-obj",
+    "473": "NOUN|PartType=Res",
+    "474": "NOUN|PartType=Res|r-nmod",
+    "475": "NOUN|PartType=Res|r-obj",
+    "476": "NOUN|Prefix=Yes",
+    "477": "NOUN|Prefix=Yes|l-acl",
+    "478": "NOUN|Prefix=Yes|l-advcl",
+    "479": "NOUN|Prefix=Yes|l-clf",
+    "480": "NOUN|Prefix=Yes|l-csubj",
+    "481": "NOUN|Prefix=Yes|l-dislocated",
+    "482": "NOUN|Prefix=Yes|l-flat",
+    "483": "NOUN|Prefix=Yes|l-nmod",
+    "484": "NOUN|Prefix=Yes|l-nsubj",
+    "485": "NOUN|Prefix=Yes|l-obj",
+    "486": "NOUN|Prefix=Yes|l-obl",
+    "487": "NOUN|Prefix=Yes|r-acl",
+    "488": "NOUN|Prefix=Yes|r-advcl",
+    "489": "NOUN|Prefix=Yes|r-advmod",
+    "490": "NOUN|Prefix=Yes|r-appos",
+    "491": "NOUN|Prefix=Yes|r-case",
+    "492": "NOUN|Prefix=Yes|r-cc",
+    "493": "NOUN|Prefix=Yes|r-ccomp",
+    "494": "NOUN|Prefix=Yes|r-clf",
+    "495": "NOUN|Prefix=Yes|r-compound",
+    "496": "NOUN|Prefix=Yes|r-conj",
+    "497": "NOUN|Prefix=Yes|r-dislocated",
+    "498": "NOUN|Prefix=Yes|r-fixed",
+    "499": "NOUN|Prefix=Yes|r-flat",
+    "500": "NOUN|Prefix=Yes|r-iobj",
+    "501": "NOUN|Prefix=Yes|r-list",
+    "502": "NOUN|Prefix=Yes|r-nmod",
+    "503": "NOUN|Prefix=Yes|r-nummod",
+    "504": "NOUN|Prefix=Yes|r-obj",
+    "505": "NOUN|Prefix=Yes|r-obl",
+    "506": "NOUN|Prefix=Yes|r-orphan",
+    "507": "NOUN|Prefix=Yes|r-xcomp",
+    "508": "NOUN|Prefix=Yes|root",
+    "509": "NOUN|l-acl",
+    "510": "NOUN|l-advcl",
+    "511": "NOUN|l-advmod",
+    "512": "NOUN|l-case",
+    "513": "NOUN|l-ccomp",
+    "514": "NOUN|l-compound",
+    "515": "NOUN|l-csubj",
+    "516": "NOUN|l-discourse",
+    "517": "NOUN|l-dislocated",
+    "518": "NOUN|l-expl",
+    "519": "NOUN|l-flat",
+    "520": "NOUN|l-iobj",
+    "521": "NOUN|l-mark",
+    "522": "NOUN|l-nmod",
+    "523": "NOUN|l-nsubj",
+    "524": "NOUN|l-nummod",
+    "525": "NOUN|l-obj",
+    "526": "NOUN|l-obl",
+    "527": "NOUN|l-orphan",
+    "528": "NOUN|l-vocative",
+    "529": "NOUN|r-acl",
+    "530": "NOUN|r-advcl",
+    "531": "NOUN|r-advmod",
+    "532": "NOUN|r-appos",
+    "533": "NOUN|r-case",
+    "534": "NOUN|r-cc",
+    "535": "NOUN|r-ccomp",
+    "536": "NOUN|r-clf",
+    "537": "NOUN|r-compound",
+    "538": "NOUN|r-conj",
+    "539": "NOUN|r-cop",
+    "540": "NOUN|r-discourse",
+    "541": "NOUN|r-dislocated",
+    "542": "NOUN|r-fixed",
+    "543": "NOUN|r-flat",
+    "544": "NOUN|r-iobj",
+    "545": "NOUN|r-list",
+    "546": "NOUN|r-mark",
+    "547": "NOUN|r-nmod",
+    "548": "NOUN|r-nsubj",
+    "549": "NOUN|r-nummod",
+    "550": "NOUN|r-obj",
+    "551": "NOUN|r-obl",
+    "552": "NOUN|r-orphan",
+    "553": "NOUN|r-parataxis",
+    "554": "NOUN|r-xcomp",
+    "555": "NOUN|root",
+    "556": "NUM",
+    "557": "NUM|Abbr=Yes",
+    "558": "NUM|Abbr=Yes|r-flat",
+    "559": "NUM|Abbr=Yes|r-nummod",
+    "560": "NUM|Abbr=Yes|r-obj",
+    "561": "NUM|Foreign=Yes",
+    "562": "NUM|Foreign=Yes|r-clf",
+    "563": "NUM|NumType=Mult",
+    "564": "NUM|NumType=Mult|l-advmod",
+    "565": "NUM|NumType=Mult|l-nummod",
+    "566": "NUM|NumType=Mult|r-advmod",
+    "567": "NUM|Prefix=Yes",
+    "568": "NUM|Prefix=Yes|l-nummod",
+    "569": "NUM|l-advcl",
+    "570": "NUM|l-advmod",
+    "571": "NUM|l-case",
+    "572": "NUM|l-clf",
+    "573": "NUM|l-dep",
+    "574": "NUM|l-flat",
+    "575": "NUM|l-nmod",
+    "576": "NUM|l-nsubj",
+    "577": "NUM|l-nummod",
+    "578": "NUM|l-obl",
+    "579": "NUM|r-acl",
+    "580": "NUM|r-advmod",
+    "581": "NUM|r-appos",
+    "582": "NUM|r-ccomp",
+    "583": "NUM|r-compound",
+    "584": "NUM|r-conj",
+    "585": "NUM|r-det",
+    "586": "NUM|r-fixed",
+    "587": "NUM|r-flat",
+    "588": "NUM|r-iobj",
+    "589": "NUM|r-nmod",
+    "590": "NUM|r-nummod",
+    "591": "NUM|r-obj",
+    "592": "NUM|r-obl",
+    "593": "NUM|root",
+    "594": "PART",
+    "595": "PART|NameType=Oth",
+    "596": "PART|NameType=Oth|l-advmod",
+    "597": "PART|NounType=Class|PartType=Emp",
+    "598": "PART|NounType=Class|PartType=Emp|Prefix=Yes",
+    "599": "PART|NounType=Class|PartType=Emp|Prefix=Yes|l-mark",
+    "600": "PART|NounType=Class|PartType=Emp|l-mark",
+    "601": "PART|NounType=Class|Prefix=Yes",
+    "602": "PART|NounType=Class|Prefix=Yes|l-mark",
+    "603": "PART|NumType=Mult|PartType=Emp",
+    "604": "PART|NumType=Mult|PartType=Emp|l-mark",
+    "605": "PART|PartType=Adj",
+    "606": "PART|PartType=Adj|l-mark",
+    "607": "PART|PartType=Adj|l-orphan",
+    "608": "PART|PartType=Adj|r-acl",
+    "609": "PART|PartType=Adj|r-compound",
+    "610": "PART|PartType=Adj|r-nmod",
+    "611": "PART|PartType=Adv",
+    "612": "PART|PartType=Adv|l-advmod",
+    "613": "PART|PartType=Adv|l-mark",
+    "614": "PART|PartType=Adv|r-advmod",
+    "615": "PART|PartType=Emp",
+    "616": "PART|PartType=Emp|Prefix=Yes",
+    "617": "PART|PartType=Emp|Prefix=Yes|l-advmod",
+    "618": "PART|PartType=Emp|Prefix=Yes|l-aux",
+    "619": "PART|PartType=Emp|Prefix=Yes|l-mark",
+    "620": "PART|PartType=Emp|l-advmod",
+    "621": "PART|PartType=Emp|l-case",
+    "622": "PART|PartType=Emp|l-discourse",
+    "623": "PART|PartType=Emp|l-mark",
+    "624": "PART|PartType=Emp|r-acl",
+    "625": "PART|PartType=Emp|r-advmod",
+    "626": "PART|PartType=Emp|r-aux",
+    "627": "PART|PartType=Emp|r-compound",
+    "628": "PART|PartType=Emp|r-det",
+    "629": "PART|PartType=Emp|r-fixed",
+    "630": "PART|PartType=Emp|r-mark",
+    "631": "PART|PartType=Emp|r-nmod",
+    "632": "PART|PartType=Enp",
+    "633": "PART|PartType=Enp|l-discourse",
+    "634": "PART|PartType=Enp|r-acl",
+    "635": "PART|PartType=Enp|r-advmod",
+    "636": "PART|PartType=Enp|r-compound",
+    "637": "PART|PartType=Enp|r-dep",
+    "638": "PART|PartType=Enp|r-det",
+    "639": "PART|PartType=Enp|r-discourse",
+    "640": "PART|PartType=Enp|r-fixed",
+    "641": "PART|PartType=Enp|r-obl",
+    "642": "PART|PartType=Int",
+    "643": "PART|PartType=Int|l-advmod",
+    "644": "PART|PartType=Int|l-mark",
+    "645": "PART|PartType=Int|r-acl",
+    "646": "PART|PartType=Int|r-advmod",
+    "647": "PART|PartType=Int|r-dep",
+    "648": "PART|PartType=Int|r-discourse",
+    "649": "PART|PartType=Int|r-nmod",
+    "650": "PART|PartType=Int|r-obj",
+    "651": "PART|PartType=Int|r-obl",
+    "652": "PART|PartType=Neg",
+    "653": "PART|PartType=Neg|l-advcl",
+    "654": "PART|PartType=Neg|l-advmod",
+    "655": "PART|PartType=Neg|l-aux",
+    "656": "PART|PartType=Neg|l-mark",
+    "657": "PART|PartType=Neg|r-acl",
+    "658": "PART|PartType=Neg|r-advmod",
+    "659": "PART|PartType=Neg|r-fixed",
+    "660": "PART|PartType=Res",
+    "661": "PART|PartType=Res|r-advmod",
+    "662": "PART|PartType=Res|r-discourse",
+    "663": "PART|PartType=Res|r-fixed",
+    "664": "PART|Prefix=Yes",
+    "665": "PART|Prefix=Yes|l-advmod",
+    "666": "PART|Prefix=Yes|l-aux",
+    "667": "PART|Prefix=Yes|l-mark",
+    "668": "PART|Prefix=Yes|r-acl",
+    "669": "PART|Prefix=Yes|r-nmod",
+    "670": "PART|l-advmod",
+    "671": "PART|l-discourse",
+    "672": "PART|l-mark",
+    "673": "PART|l-nsubj",
+    "674": "PART|r-acl",
+    "675": "PART|r-advmod",
+    "676": "PART|r-discourse",
+    "677": "PART|r-fixed",
+    "678": "PART|r-mark",
+    "679": "PART|r-obj",
+    "680": "PRON",
+    "681": "PRON|NounType=Class",
+    "682": "PRON|NounType=Class|r-clf",
+    "683": "PRON|PronType=Prs",
+    "684": "PRON|PronType=Prs|l-advmod",
+    "685": "PRON|PronType=Prs|l-expl",
+    "686": "PRON|PronType=Prs|l-nsubj",
+    "687": "PRON|PronType=Prs|l-obj",
+    "688": "PRON|PronType=Prs|l-obl",
+    "689": "PRON|PronType=Prs|r-advcl",
+    "690": "PRON|PronType=Prs|r-advmod",
+    "691": "PRON|PronType=Prs|r-ccomp",
+    "692": "PRON|PronType=Prs|r-clf",
+    "693": "PRON|PronType=Prs|r-conj",
+    "694": "PRON|PronType=Prs|r-nmod",
+    "695": "PRON|PronType=Prs|r-nsubj",
+    "696": "PRON|PronType=Prs|r-obj",
+    "697": "PRON|PronType=Prs|r-obl",
+    "698": "PRON|PronType=Prs|root",
+    "699": "PRON|PronType=Rcp",
+    "700": "PRON|PronType=Rcp|r-advmod",
+    "701": "PRON|PronType=Rcp|r-iobj",
+    "702": "PRON|PronType=Rcp|r-nmod",
+    "703": "PRON|PronType=Rcp|r-obj",
+    "704": "PRON|PronType=Rcp|r-obl",
+    "705": "PRON|l-advcl",
+    "706": "PRON|l-advmod",
+    "707": "PRON|l-compound",
+    "708": "PRON|l-csubj",
+    "709": "PRON|l-dislocated",
+    "710": "PRON|l-expl",
+    "711": "PRON|l-iobj",
+    "712": "PRON|l-mark",
+    "713": "PRON|l-nsubj",
+    "714": "PRON|l-obj",
+    "715": "PRON|l-obl",
+    "716": "PRON|r-acl",
+    "717": "PRON|r-advmod",
+    "718": "PRON|r-appos",
+    "719": "PRON|r-ccomp",
+    "720": "PRON|r-compound",
+    "721": "PRON|r-conj",
+    "722": "PRON|r-det",
+    "723": "PRON|r-discourse",
+    "724": "PRON|r-fixed",
+    "725": "PRON|r-flat",
+    "726": "PRON|r-iobj",
+    "727": "PRON|r-nmod",
+    "728": "PRON|r-nsubj",
+    "729": "PRON|r-obj",
+    "730": "PRON|r-obl",
+    "731": "PROPN",
+    "732": "PROPN|Abbr=Yes",
+    "733": "PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth",
+    "734": "PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth|r-obj",
+    "735": "PROPN|Abbr=Yes|NameType=Com",
+    "736": "PROPN|Abbr=Yes|NameType=Com|r-advmod",
+    "737": "PROPN|Abbr=Yes|NameType=Com|r-nmod",
+    "738": "PROPN|Abbr=Yes|l-nmod",
+    "739": "PROPN|Abbr=Yes|l-nsubj",
+    "740": "PROPN|Abbr=Yes|r-nmod",
+    "741": "PROPN|Foreign=Yes",
+    "742": "PROPN|Foreign=Yes|NameType=Com",
+    "743": "PROPN|Foreign=Yes|NameType=Com|l-nsubj",
+    "744": "PROPN|Foreign=Yes|NameType=Com|r-list",
+    "745": "PROPN|Foreign=Yes|NameType=Com|r-nmod",
+    "746": "PROPN|Foreign=Yes|NameType=Com|r-obl",
+    "747": "PROPN|Foreign=Yes|NameType=Geo",
+    "748": "PROPN|Foreign=Yes|NameType=Geo|r-obj",
+    "749": "PROPN|Foreign=Yes|NameType=Geo|r-obl",
+    "750": "PROPN|Foreign=Yes|NameType=Giv",
+    "751": "PROPN|Foreign=Yes|NameType=Giv|l-nsubj",
+    "752": "PROPN|Foreign=Yes|NameType=Oth",
+    "753": "PROPN|Foreign=Yes|NameType=Oth|r-conj",
+    "754": "PROPN|Foreign=Yes|NameType=Oth|r-flat",
+    "755": "PROPN|Foreign=Yes|NameType=Oth|r-nmod",
+    "756": "PROPN|Foreign=Yes|NameType=Prs",
+    "757": "PROPN|Foreign=Yes|NameType=Prs|l-flat",
+    "758": "PROPN|Foreign=Yes|NameType=Prs|l-nsubj",
+    "759": "PROPN|Foreign=Yes|NameType=Prs|r-conj",
+    "760": "PROPN|Foreign=Yes|NameType=Prs|r-flat",
+    "761": "PROPN|Foreign=Yes|NameType=Prs|r-nmod",
+    "762": "PROPN|Foreign=Yes|NameType=Prs|r-obj",
+    "763": "PROPN|Foreign=Yes|NameType=Prs|r-obl",
+    "764": "PROPN|Foreign=Yes|NameType=Sur",
+    "765": "PROPN|Foreign=Yes|NameType=Sur|r-flat",
+    "766": "PROPN|Foreign=Yes|l-flat",
+    "767": "PROPN|Foreign=Yes|l-nmod",
+    "768": "PROPN|Foreign=Yes|l-nsubj",
+    "769": "PROPN|Foreign=Yes|l-obl",
+    "770": "PROPN|Foreign=Yes|r-appos",
+    "771": "PROPN|Foreign=Yes|r-ccomp",
+    "772": "PROPN|Foreign=Yes|r-compound",
+    "773": "PROPN|Foreign=Yes|r-conj",
+    "774": "PROPN|Foreign=Yes|r-flat",
+    "775": "PROPN|Foreign=Yes|r-iobj",
+    "776": "PROPN|Foreign=Yes|r-list",
+    "777": "PROPN|Foreign=Yes|r-nmod",
+    "778": "PROPN|Foreign=Yes|r-nsubj",
+    "779": "PROPN|Foreign=Yes|r-obj",
+    "780": "PROPN|Foreign=Yes|r-obl",
+    "781": "PROPN|Foreign=Yes|root",
+    "782": "PROPN|NameType=Com",
+    "783": "PROPN|NameType=Com|l-nsubj",
+    "784": "PROPN|NameType=Com|l-obl",
+    "785": "PROPN|NameType=Com|r-appos",
+    "786": "PROPN|NameType=Com|r-conj",
+    "787": "PROPN|NameType=Com|r-flat",
+    "788": "PROPN|NameType=Com|r-list",
+    "789": "PROPN|NameType=Com|r-nmod",
+    "790": "PROPN|NameType=Com|r-nsubj",
+    "791": "PROPN|NameType=Com|r-obj",
+    "792": "PROPN|NameType=Com|r-obl",
+    "793": "PROPN|NameType=Geo",
+    "794": "PROPN|NameType=Geo|l-nsubj",
+    "795": "PROPN|NameType=Geo|l-obl",
+    "796": "PROPN|NameType=Geo|r-compound",
+    "797": "PROPN|NameType=Geo|r-conj",
+    "798": "PROPN|NameType=Geo|r-flat",
+    "799": "PROPN|NameType=Geo|r-list",
+    "800": "PROPN|NameType=Geo|r-nmod",
+    "801": "PROPN|NameType=Geo|r-nsubj",
+    "802": "PROPN|NameType=Geo|r-nummod",
+    "803": "PROPN|NameType=Geo|r-obj",
+    "804": "PROPN|NameType=Geo|r-obl",
+    "805": "PROPN|NameType=Geo|root",
+    "806": "PROPN|NameType=Giv",
+    "807": "PROPN|NameType=Giv|l-dislocated",
+    "808": "PROPN|NameType=Giv|l-nsubj",
+    "809": "PROPN|NameType=Giv|l-obl",
+    "810": "PROPN|NameType=Giv|r-acl",
+    "811": "PROPN|NameType=Giv|r-appos",
+    "812": "PROPN|NameType=Giv|r-ccomp",
+    "813": "PROPN|NameType=Giv|r-conj",
+    "814": "PROPN|NameType=Giv|r-flat",
+    "815": "PROPN|NameType=Giv|r-list",
+    "816": "PROPN|NameType=Giv|r-nmod",
+    "817": "PROPN|NameType=Giv|r-nsubj",
+    "818": "PROPN|NameType=Giv|r-obj",
+    "819": "PROPN|NameType=Giv|r-obl",
+    "820": "PROPN|NameType=Giv|root",
+    "821": "PROPN|NameType=Nat",
+    "822": "PROPN|NameType=Nat|l-csubj",
+    "823": "PROPN|NameType=Nat|l-nsubj",
+    "824": "PROPN|NameType=Nat|l-obl",
+    "825": "PROPN|NameType=Nat|r-acl",
+    "826": "PROPN|NameType=Nat|r-appos",
+    "827": "PROPN|NameType=Nat|r-compound",
+    "828": "PROPN|NameType=Nat|r-conj",
+    "829": "PROPN|NameType=Nat|r-flat",
+    "830": "PROPN|NameType=Nat|r-list",
+    "831": "PROPN|NameType=Nat|r-nmod",
+    "832": "PROPN|NameType=Nat|r-nummod",
+    "833": "PROPN|NameType=Nat|r-obj",
+    "834": "PROPN|NameType=Nat|r-obl",
+    "835": "PROPN|NameType=Oth",
+    "836": "PROPN|NameType=Oth|l-dislocated",
+    "837": "PROPN|NameType=Oth|l-nsubj",
+    "838": "PROPN|NameType=Oth|r-acl",
+    "839": "PROPN|NameType=Oth|r-appos",
+    "840": "PROPN|NameType=Oth|r-compound",
+    "841": "PROPN|NameType=Oth|r-conj",
+    "842": "PROPN|NameType=Oth|r-flat",
+    "843": "PROPN|NameType=Oth|r-nmod",
+    "844": "PROPN|NameType=Oth|r-obj",
+    "845": "PROPN|NameType=Oth|r-obl",
+    "846": "PROPN|NameType=Oth|root",
+    "847": "PROPN|NameType=Pro",
+    "848": "PROPN|NameType=Pro|l-nsubj",
+    "849": "PROPN|NameType=Pro|l-obl",
+    "850": "PROPN|NameType=Pro|r-advcl",
+    "851": "PROPN|NameType=Pro|r-flat",
+    "852": "PROPN|NameType=Pro|r-nmod",
+    "853": "PROPN|NameType=Pro|r-obj",
+    "854": "PROPN|NameType=Prs",
+    "855": "PROPN|NameType=Prs|l-dislocated",
+    "856": "PROPN|NameType=Prs|l-nsubj",
+    "857": "PROPN|NameType=Prs|l-obl",
+    "858": "PROPN|NameType=Prs|l-vocative",
+    "859": "PROPN|NameType=Prs|r-conj",
+    "860": "PROPN|NameType=Prs|r-discourse",
+    "861": "PROPN|NameType=Prs|r-flat",
+    "862": "PROPN|NameType=Prs|r-list",
+    "863": "PROPN|NameType=Prs|r-nmod",
+    "864": "PROPN|NameType=Prs|r-obj",
+    "865": "PROPN|NameType=Prs|r-obl",
+    "866": "PROPN|NameType=Prs|r-vocative",
+    "867": "PROPN|NameType=Sur",
+    "868": "PROPN|NameType=Sur|l-nsubj",
+    "869": "PROPN|NameType=Sur|r-flat",
+    "870": "PROPN|NameType=Sur|r-nmod",
+    "871": "PROPN|NounType=Class",
+    "872": "PROPN|NounType=Class|r-clf",
+    "873": "PROPN|Prefix=Yes",
+    "874": "PROPN|Prefix=Yes|l-nsubj",
+    "875": "PROPN|Prefix=Yes|r-nmod",
+    "876": "PROPN|l-advmod",
+    "877": "PROPN|l-nsubj",
+    "878": "PROPN|l-obl",
+    "879": "PROPN|r-acl",
+    "880": "PROPN|r-advmod",
+    "881": "PROPN|r-appos",
+    "882": "PROPN|r-clf",
+    "883": "PROPN|r-compound",
+    "884": "PROPN|r-conj",
+    "885": "PROPN|r-fixed",
+    "886": "PROPN|r-flat",
+    "887": "PROPN|r-iobj",
+    "888": "PROPN|r-list",
+    "889": "PROPN|r-nmod",
+    "890": "PROPN|r-obj",
+    "891": "PROPN|r-obl",
+    "892": "PROPN|root",
+    "893": "PUNCT",
+    "894": "PUNCT|NounType=Class",
+    "895": "PUNCT|NounType=Class|r-punct",
+    "896": "PUNCT|l-advmod",
+    "897": "PUNCT|l-dep",
+    "898": "PUNCT|l-punct",
+    "899": "PUNCT|r-dep",
+    "900": "PUNCT|r-punct",
+    "901": "SCONJ",
+    "902": "SCONJ|NumType=Mult",
+    "903": "SCONJ|NumType=Mult|l-mark",
+    "904": "SCONJ|Prefix=Yes",
+    "905": "SCONJ|Prefix=Yes|l-cc",
+    "906": "SCONJ|Prefix=Yes|l-mark",
+    "907": "SCONJ|VerbType=Cop",
+    "908": "SCONJ|VerbType=Cop|l-mark",
+    "909": "SCONJ|l-advmod",
+    "910": "SCONJ|l-case",
+    "911": "SCONJ|l-cc",
+    "912": "SCONJ|l-discourse",
+    "913": "SCONJ|l-mark",
+    "914": "SCONJ|l-nsubj",
+    "915": "SCONJ|l-orphan",
+    "916": "SCONJ|r-advcl",
+    "917": "SCONJ|r-compound",
+    "918": "SCONJ|r-fixed",
+    "919": "SCONJ|r-flat",
+    "920": "SCONJ|r-mark",
+    "921": "SCONJ|r-orphan",
+    "922": "SCONJ|root",
+    "923": "SYM",
+    "924": "SYM|l-dep",
+    "925": "SYM|r-clf",
+    "926": "SYM|r-nmod",
+    "927": "SYM|r-obj",
+    "928": "SYM|r-obl",
+    "929": "SYM|r-xcomp",
+    "930": "VERB",
+    "931": "VERB|Abbr=Yes",
+    "932": "VERB|Abbr=Yes|r-acl",
+    "933": "VERB|Foreign=Yes",
+    "934": "VERB|Foreign=Yes|l-nsubj",
+    "935": "VERB|Foreign=Yes|r-acl",
+    "936": "VERB|Foreign=Yes|r-advcl",
+    "937": "VERB|Foreign=Yes|r-ccomp",
+    "938": "VERB|Foreign=Yes|r-compound",
+    "939": "VERB|Foreign=Yes|r-conj",
+    "940": "VERB|Foreign=Yes|r-flat",
+    "941": "VERB|Foreign=Yes|r-nmod",
+    "942": "VERB|Foreign=Yes|r-xcomp",
+    "943": "VERB|Foreign=Yes|root",
+    "944": "VERB|NounType=Class",
+    "945": "VERB|NounType=Class|r-acl",
+    "946": "VERB|NounType=Class|r-compound",
+    "947": "VERB|PartType=Adj",
+    "948": "VERB|PartType=Adj|r-acl",
+    "949": "VERB|Prefix=Yes",
+    "950": "VERB|Prefix=Yes|l-acl",
+    "951": "VERB|Prefix=Yes|l-nsubj",
+    "952": "VERB|Prefix=Yes|r-acl",
+    "953": "VERB|Prefix=Yes|r-advcl",
+    "954": "VERB|Prefix=Yes|r-ccomp",
+    "955": "VERB|Prefix=Yes|r-compound",
+    "956": "VERB|Prefix=Yes|r-conj",
+    "957": "VERB|Prefix=Yes|r-parataxis",
+    "958": "VERB|Prefix=Yes|root",
+    "959": "VERB|VerbType=Cop",
+    "960": "VERB|VerbType=Cop|l-advmod",
+    "961": "VERB|VerbType=Cop|l-cop",
+    "962": "VERB|VerbType=Cop|r-acl",
+    "963": "VERB|VerbType=Cop|r-advcl",
+    "964": "VERB|VerbType=Cop|r-ccomp",
+    "965": "VERB|VerbType=Cop|r-compound",
+    "966": "VERB|VerbType=Cop|r-parataxis",
+    "967": "VERB|VerbType=Cop|root",
+    "968": "VERB|l-acl",
+    "969": "VERB|l-advcl",
+    "970": "VERB|l-advmod",
+    "971": "VERB|l-aux",
+    "972": "VERB|l-case",
+    "973": "VERB|l-cc",
+    "974": "VERB|l-ccomp",
+    "975": "VERB|l-compound",
+    "976": "VERB|l-conj",
+    "977": "VERB|l-cop",
+    "978": "VERB|l-csubj",
+    "979": "VERB|l-discourse",
+    "980": "VERB|l-dislocated",
+    "981": "VERB|l-mark",
+    "982": "VERB|l-nsubj",
+    "983": "VERB|l-obl",
+    "984": "VERB|l-orphan",
+    "985": "VERB|l-xcomp",
+    "986": "VERB|r-acl",
+    "987": "VERB|r-advcl",
+    "988": "VERB|r-advmod",
+    "989": "VERB|r-appos",
+    "990": "VERB|r-aux",
+    "991": "VERB|r-case",
+    "992": "VERB|r-cc",
+    "993": "VERB|r-ccomp",
+    "994": "VERB|r-clf",
+    "995": "VERB|r-compound",
+    "996": "VERB|r-conj",
+    "997": "VERB|r-dep",
+    "998": "VERB|r-det",
+    "999": "VERB|r-discourse",
+    "1000": "VERB|r-fixed",
+    "1001": "VERB|r-flat",
+    "1002": "VERB|r-list",
+    "1003": "VERB|r-mark",
+    "1004": "VERB|r-nmod",
+    "1005": "VERB|r-nsubj",
+    "1006": "VERB|r-obj",
+    "1007": "VERB|r-obl",
+    "1008": "VERB|r-orphan",
+    "1009": "VERB|r-parataxis",
+    "1010": "VERB|r-punct",
+    "1011": "VERB|r-xcomp",
+    "1012": "VERB|root"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "label2id": {
+    "ADP": 0,
+    "ADP|Foreign=Yes": 1,
+    "ADP|Foreign=Yes|l-case": 2,
+    "ADP|NounType=Class": 3,
+    "ADP|NounType=Class|l-case": 4,
+    "ADP|Prefix=Yes": 5,
+    "ADP|Prefix=Yes|l-case": 6,
+    "ADP|Prefix=Yes|l-mark": 7,
+    "ADP|l-acl": 8,
+    "ADP|l-advcl": 9,
+    "ADP|l-advmod": 10,
+    "ADP|l-case": 11,
+    "ADP|l-cc": 12,
+    "ADP|l-dep": 13,
+    "ADP|l-fixed": 14,
+    "ADP|l-flat": 15,
+    "ADP|l-mark": 16,
+    "ADP|l-nmod": 17,
+    "ADP|l-nsubj": 18,
+    "ADP|l-obl": 19,
+    "ADP|l-orphan": 20,
+    "ADP|r-acl": 21,
+    "ADP|r-advmod": 22,
+    "ADP|r-case": 23,
+    "ADP|r-compound": 24,
+    "ADP|r-conj": 25,
+    "ADP|r-fixed": 26,
+    "ADP|r-flat": 27,
+    "ADP|r-obl": 28,
+    "ADP|r-orphan": 29,
+    "ADP|root": 30,
+    "ADV": 31,
+    "ADV|Foreign=Yes": 32,
+    "ADV|Foreign=Yes|l-advmod": 33,
+    "ADV|Foreign=Yes|r-advmod": 34,
+    "ADV|NumType=Mult": 35,
+    "ADV|NumType=Mult|r-advmod": 36,
+    "ADV|PartType=Adv": 37,
+    "ADV|PartType=Adv|l-advmod": 38,
+    "ADV|PartType=Adv|l-mark": 39,
+    "ADV|PartType=Adv|r-advmod": 40,
+    "ADV|PartType=Enp": 41,
+    "ADV|PartType=Enp|l-advmod": 42,
+    "ADV|PartType=Enp|r-advmod": 43,
+    "ADV|PartType=Int": 44,
+    "ADV|PartType=Int|r-advmod": 45,
+    "ADV|PartType=Int|r-fixed": 46,
+    "ADV|Prefix=Yes": 47,
+    "ADV|Prefix=Yes|l-advmod": 48,
+    "ADV|Prefix=Yes|l-mark": 49,
+    "ADV|Prefix=Yes|r-advmod": 50,
+    "ADV|l-acl": 51,
+    "ADV|l-advcl": 52,
+    "ADV|l-advmod": 53,
+    "ADV|l-aux": 54,
+    "ADV|l-case": 55,
+    "ADV|l-compound": 56,
+    "ADV|l-dep": 57,
+    "ADV|l-det": 58,
+    "ADV|l-discourse": 59,
+    "ADV|l-fixed": 60,
+    "ADV|l-mark": 61,
+    "ADV|l-orphan": 62,
+    "ADV|r-acl": 63,
+    "ADV|r-advcl": 64,
+    "ADV|r-advmod": 65,
+    "ADV|r-aux": 66,
+    "ADV|r-compound": 67,
+    "ADV|r-conj": 68,
+    "ADV|r-det": 69,
+    "ADV|r-fixed": 70,
+    "ADV|r-flat": 71,
+    "ADV|r-mark": 72,
+    "ADV|r-nmod": 73,
+    "ADV|r-obj": 74,
+    "ADV|r-orphan": 75,
+    "ADV|r-xcomp": 76,
+    "ADV|root": 77,
+    "AUX": 78,
+    "AUX|Foreign=Yes": 79,
+    "AUX|Foreign=Yes|l-aux": 80,
+    "AUX|NounType=Class": 81,
+    "AUX|NounType=Class|r-appos": 82,
+    "AUX|Prefix=Yes": 83,
+    "AUX|Prefix=Yes|l-aux": 84,
+    "AUX|Prefix=Yes|r-aux": 85,
+    "AUX|VerbType=Cop": 86,
+    "AUX|VerbType=Cop|l-acl": 87,
+    "AUX|VerbType=Cop|l-advcl": 88,
+    "AUX|VerbType=Cop|l-aux": 89,
+    "AUX|VerbType=Cop|l-cop": 90,
+    "AUX|VerbType=Cop|r-acl": 91,
+    "AUX|VerbType=Cop|r-advcl": 92,
+    "AUX|VerbType=Cop|r-aux": 93,
+    "AUX|VerbType=Cop|r-conj": 94,
+    "AUX|VerbType=Cop|r-mark": 95,
+    "AUX|VerbType=Cop|root": 96,
+    "AUX|l-advmod": 97,
+    "AUX|l-aux": 98,
+    "AUX|l-cop": 99,
+    "AUX|l-mark": 100,
+    "AUX|r-acl": 101,
+    "AUX|r-advmod": 102,
+    "AUX|r-aux": 103,
+    "AUX|r-ccomp": 104,
+    "AUX|r-clf": 105,
+    "AUX|r-compound": 106,
+    "AUX|r-conj": 107,
+    "AUX|r-fixed": 108,
+    "AUX|root": 109,
+    "B-ADP": 110,
+    "B-ADP|Foreign=Yes": 111,
+    "B-ADP|NounType=Class": 112,
+    "B-ADP|Prefix=Yes": 113,
+    "B-ADV": 114,
+    "B-ADV|Foreign=Yes": 115,
+    "B-ADV|NumType=Mult": 116,
+    "B-ADV|PartType=Adv": 117,
+    "B-ADV|PartType=Enp": 118,
+    "B-ADV|PartType=Int": 119,
+    "B-ADV|Prefix=Yes": 120,
+    "B-AUX": 121,
+    "B-AUX|Foreign=Yes": 122,
+    "B-AUX|NounType=Class": 123,
+    "B-AUX|Prefix=Yes": 124,
+    "B-AUX|VerbType=Cop": 125,
+    "B-CCONJ": 126,
+    "B-CCONJ|Foreign=Yes": 127,
+    "B-CCONJ|PronType=Prs": 128,
+    "B-DET": 129,
+    "B-DET|NumType=Mult": 130,
+    "B-DET|PartType=Emp": 131,
+    "B-DET|PartType=Int": 132,
+    "B-NOUN": 133,
+    "B-NOUN|Abbr=Yes": 134,
+    "B-NOUN|Abbr=Yes|Foreign=Yes": 135,
+    "B-NOUN|Abbr=Yes|Prefix=Yes": 136,
+    "B-NOUN|Foreign=Yes": 137,
+    "B-NOUN|Foreign=Yes|NounType=Class": 138,
+    "B-NOUN|Foreign=Yes|Prefix=Yes": 139,
+    "B-NOUN|NameType=Com": 140,
+    "B-NOUN|NameType=Geo": 141,
+    "B-NOUN|NameType=Nat": 142,
+    "B-NOUN|NameType=Oth": 143,
+    "B-NOUN|NameType=Pro": 144,
+    "B-NOUN|NameType=Prs": 145,
+    "B-NOUN|NounType=Class": 146,
+    "B-NOUN|NounType=Class|Prefix=Yes": 147,
+    "B-NOUN|NumType=Mult": 148,
+    "B-NOUN|PartType=Enp": 149,
+    "B-NOUN|PartType=Int": 150,
+    "B-NOUN|PartType=Res": 151,
+    "B-NOUN|Prefix=Yes": 152,
+    "B-NUM": 153,
+    "B-NUM|Abbr=Yes": 154,
+    "B-NUM|Foreign=Yes": 155,
+    "B-NUM|NumType=Mult": 156,
+    "B-NUM|Prefix=Yes": 157,
+    "B-PART": 158,
+    "B-PART|NameType=Oth": 159,
+    "B-PART|NounType=Class|PartType=Emp": 160,
+    "B-PART|NounType=Class|PartType=Emp|Prefix=Yes": 161,
+    "B-PART|NounType=Class|Prefix=Yes": 162,
+    "B-PART|NumType=Mult|PartType=Emp": 163,
+    "B-PART|PartType=Adj": 164,
+    "B-PART|PartType=Adv": 165,
+    "B-PART|PartType=Emp": 166,
+    "B-PART|PartType=Emp|Prefix=Yes": 167,
+    "B-PART|PartType=Enp": 168,
+    "B-PART|PartType=Int": 169,
+    "B-PART|PartType=Neg": 170,
+    "B-PART|PartType=Res": 171,
+    "B-PART|Prefix=Yes": 172,
+    "B-PRON": 173,
+    "B-PRON|NounType=Class": 174,
+    "B-PRON|PronType=Prs": 175,
+    "B-PRON|PronType=Rcp": 176,
+    "B-PROPN": 177,
+    "B-PROPN|Abbr=Yes": 178,
+    "B-PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth": 179,
+    "B-PROPN|Abbr=Yes|NameType=Com": 180,
+    "B-PROPN|Foreign=Yes": 181,
+    "B-PROPN|Foreign=Yes|NameType=Com": 182,
+    "B-PROPN|Foreign=Yes|NameType=Geo": 183,
+    "B-PROPN|Foreign=Yes|NameType=Giv": 184,
+    "B-PROPN|Foreign=Yes|NameType=Oth": 185,
+    "B-PROPN|Foreign=Yes|NameType=Prs": 186,
+    "B-PROPN|Foreign=Yes|NameType=Sur": 187,
+    "B-PROPN|NameType=Com": 188,
+    "B-PROPN|NameType=Geo": 189,
+    "B-PROPN|NameType=Giv": 190,
+    "B-PROPN|NameType=Nat": 191,
+    "B-PROPN|NameType=Oth": 192,
+    "B-PROPN|NameType=Pro": 193,
+    "B-PROPN|NameType=Prs": 194,
+    "B-PROPN|NameType=Sur": 195,
+    "B-PROPN|NounType=Class": 196,
+    "B-PROPN|Prefix=Yes": 197,
+    "B-PUNCT": 198,
+    "B-PUNCT|NounType=Class": 199,
+    "B-SCONJ": 200,
+    "B-SCONJ|NumType=Mult": 201,
+    "B-SCONJ|Prefix=Yes": 202,
+    "B-SCONJ|VerbType=Cop": 203,
+    "B-SYM": 204,
+    "B-VERB": 205,
+    "B-VERB|Abbr=Yes": 206,
+    "B-VERB|Foreign=Yes": 207,
+    "B-VERB|NounType=Class": 208,
+    "B-VERB|PartType=Adj": 209,
+    "B-VERB|Prefix=Yes": 210,
+    "B-VERB|VerbType=Cop": 211,
+    "CCONJ": 212,
+    "CCONJ|Foreign=Yes": 213,
+    "CCONJ|Foreign=Yes|l-cc": 214,
+    "CCONJ|PronType=Prs": 215,
+    "CCONJ|PronType=Prs|l-cc": 216,
+    "CCONJ|l-advmod": 217,
+    "CCONJ|l-case": 218,
+    "CCONJ|l-cc": 219,
+    "CCONJ|l-conj": 220,
+    "CCONJ|l-discourse": 221,
+    "CCONJ|l-fixed": 222,
+    "CCONJ|l-flat": 223,
+    "CCONJ|l-mark": 224,
+    "CCONJ|l-nsubj": 225,
+    "CCONJ|l-obj": 226,
+    "CCONJ|l-orphan": 227,
+    "CCONJ|r-cc": 228,
+    "CCONJ|r-compound": 229,
+    "CCONJ|r-fixed": 230,
+    "CCONJ|r-mark": 231,
+    "DET": 232,
+    "DET|NumType=Mult": 233,
+    "DET|NumType=Mult|l-det": 234,
+    "DET|PartType=Emp": 235,
+    "DET|PartType=Emp|r-det": 236,
+    "DET|PartType=Int": 237,
+    "DET|PartType=Int|r-det": 238,
+    "DET|l-compound": 239,
+    "DET|l-det": 240,
+    "DET|l-discourse": 241,
+    "DET|l-nsubj": 242,
+    "DET|l-obl": 243,
+    "DET|l-orphan": 244,
+    "DET|r-advmod": 245,
+    "DET|r-compound": 246,
+    "DET|r-conj": 247,
+    "DET|r-dep": 248,
+    "DET|r-det": 249,
+    "DET|r-fixed": 250,
+    "DET|r-flat": 251,
+    "DET|r-list": 252,
+    "DET|r-nmod": 253,
+    "DET|r-nummod": 254,
+    "DET|r-obl": 255,
+    "DET|r-orphan": 256,
+    "I-ADP": 257,
+    "I-ADP|Foreign=Yes": 258,
+    "I-ADP|NounType=Class": 259,
+    "I-ADP|Prefix=Yes": 260,
+    "I-ADV": 261,
+    "I-ADV|Foreign=Yes": 262,
+    "I-ADV|NumType=Mult": 263,
+    "I-ADV|PartType=Adv": 264,
+    "I-ADV|PartType=Enp": 265,
+    "I-ADV|PartType=Int": 266,
+    "I-ADV|Prefix=Yes": 267,
+    "I-AUX": 268,
+    "I-AUX|Foreign=Yes": 269,
+    "I-AUX|NounType=Class": 270,
+    "I-AUX|Prefix=Yes": 271,
+    "I-AUX|VerbType=Cop": 272,
+    "I-CCONJ": 273,
+    "I-CCONJ|Foreign=Yes": 274,
+    "I-CCONJ|PronType=Prs": 275,
+    "I-DET": 276,
+    "I-DET|NumType=Mult": 277,
+    "I-DET|PartType=Emp": 278,
+    "I-DET|PartType=Int": 279,
+    "I-NOUN": 280,
+    "I-NOUN|Abbr=Yes": 281,
+    "I-NOUN|Abbr=Yes|Foreign=Yes": 282,
+    "I-NOUN|Abbr=Yes|Prefix=Yes": 283,
+    "I-NOUN|Foreign=Yes": 284,
+    "I-NOUN|Foreign=Yes|NounType=Class": 285,
+    "I-NOUN|Foreign=Yes|Prefix=Yes": 286,
+    "I-NOUN|NameType=Com": 287,
+    "I-NOUN|NameType=Geo": 288,
+    "I-NOUN|NameType=Nat": 289,
+    "I-NOUN|NameType=Oth": 290,
+    "I-NOUN|NameType=Pro": 291,
+    "I-NOUN|NameType=Prs": 292,
+    "I-NOUN|NounType=Class": 293,
+    "I-NOUN|NounType=Class|Prefix=Yes": 294,
+    "I-NOUN|NumType=Mult": 295,
+    "I-NOUN|PartType=Enp": 296,
+    "I-NOUN|PartType=Int": 297,
+    "I-NOUN|PartType=Res": 298,
+    "I-NOUN|Prefix=Yes": 299,
+    "I-NUM": 300,
+    "I-NUM|Abbr=Yes": 301,
+    "I-NUM|Foreign=Yes": 302,
+    "I-NUM|NumType=Mult": 303,
+    "I-NUM|Prefix=Yes": 304,
+    "I-PART": 305,
+    "I-PART|NameType=Oth": 306,
+    "I-PART|NounType=Class|PartType=Emp": 307,
+    "I-PART|NounType=Class|PartType=Emp|Prefix=Yes": 308,
+    "I-PART|NounType=Class|Prefix=Yes": 309,
+    "I-PART|NumType=Mult|PartType=Emp": 310,
+    "I-PART|PartType=Adj": 311,
+    "I-PART|PartType=Adv": 312,
+    "I-PART|PartType=Emp": 313,
+    "I-PART|PartType=Emp|Prefix=Yes": 314,
+    "I-PART|PartType=Enp": 315,
+    "I-PART|PartType=Int": 316,
+    "I-PART|PartType=Neg": 317,
+    "I-PART|PartType=Res": 318,
+    "I-PART|Prefix=Yes": 319,
+    "I-PRON": 320,
+    "I-PRON|NounType=Class": 321,
+    "I-PRON|PronType=Prs": 322,
+    "I-PRON|PronType=Rcp": 323,
+    "I-PROPN": 324,
+    "I-PROPN|Abbr=Yes": 325,
+    "I-PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth": 326,
+    "I-PROPN|Abbr=Yes|NameType=Com": 327,
+    "I-PROPN|Foreign=Yes": 328,
+    "I-PROPN|Foreign=Yes|NameType=Com": 329,
+    "I-PROPN|Foreign=Yes|NameType=Geo": 330,
+    "I-PROPN|Foreign=Yes|NameType=Giv": 331,
+    "I-PROPN|Foreign=Yes|NameType=Oth": 332,
+    "I-PROPN|Foreign=Yes|NameType=Prs": 333,
+    "I-PROPN|Foreign=Yes|NameType=Sur": 334,
+    "I-PROPN|NameType=Com": 335,
+    "I-PROPN|NameType=Geo": 336,
+    "I-PROPN|NameType=Giv": 337,
+    "I-PROPN|NameType=Nat": 338,
+    "I-PROPN|NameType=Oth": 339,
+    "I-PROPN|NameType=Pro": 340,
+    "I-PROPN|NameType=Prs": 341,
+    "I-PROPN|NameType=Sur": 342,
+    "I-PROPN|NounType=Class": 343,
+    "I-PROPN|Prefix=Yes": 344,
+    "I-PUNCT": 345,
+    "I-PUNCT|NounType=Class": 346,
+    "I-SCONJ": 347,
+    "I-SCONJ|NumType=Mult": 348,
+    "I-SCONJ|Prefix=Yes": 349,
+    "I-SCONJ|VerbType=Cop": 350,
+    "I-SYM": 351,
+    "I-VERB": 352,
+    "I-VERB|Abbr=Yes": 353,
+    "I-VERB|Foreign=Yes": 354,
+    "I-VERB|NounType=Class": 355,
+    "I-VERB|PartType=Adj": 356,
+    "I-VERB|Prefix=Yes": 357,
+    "I-VERB|VerbType=Cop": 358,
+    "NOUN": 359,
+    "NOUN|Abbr=Yes": 360,
+    "NOUN|Abbr=Yes|Foreign=Yes": 361,
+    "NOUN|Abbr=Yes|Foreign=Yes|r-nmod": 362,
+    "NOUN|Abbr=Yes|Prefix=Yes": 363,
+    "NOUN|Abbr=Yes|Prefix=Yes|l-flat": 364,
+    "NOUN|Abbr=Yes|l-flat": 365,
+    "NOUN|Abbr=Yes|l-nmod": 366,
+    "NOUN|Abbr=Yes|l-nsubj": 367,
+    "NOUN|Abbr=Yes|l-obl": 368,
+    "NOUN|Abbr=Yes|r-acl": 369,
+    "NOUN|Abbr=Yes|r-appos": 370,
+    "NOUN|Abbr=Yes|r-clf": 371,
+    "NOUN|Abbr=Yes|r-conj": 372,
+    "NOUN|Abbr=Yes|r-fixed": 373,
+    "NOUN|Abbr=Yes|r-flat": 374,
+    "NOUN|Abbr=Yes|r-nmod": 375,
+    "NOUN|Abbr=Yes|r-obj": 376,
+    "NOUN|Abbr=Yes|r-obl": 377,
+    "NOUN|Foreign=Yes": 378,
+    "NOUN|Foreign=Yes|NounType=Class": 379,
+    "NOUN|Foreign=Yes|NounType=Class|r-clf": 380,
+    "NOUN|Foreign=Yes|NounType=Class|r-obj": 381,
+    "NOUN|Foreign=Yes|Prefix=Yes": 382,
+    "NOUN|Foreign=Yes|Prefix=Yes|l-flat": 383,
+    "NOUN|Foreign=Yes|Prefix=Yes|r-appos": 384,
+    "NOUN|Foreign=Yes|l-dislocated": 385,
+    "NOUN|Foreign=Yes|l-flat": 386,
+    "NOUN|Foreign=Yes|l-nmod": 387,
+    "NOUN|Foreign=Yes|l-nsubj": 388,
+    "NOUN|Foreign=Yes|l-obl": 389,
+    "NOUN|Foreign=Yes|r-acl": 390,
+    "NOUN|Foreign=Yes|r-advcl": 391,
+    "NOUN|Foreign=Yes|r-advmod": 392,
+    "NOUN|Foreign=Yes|r-appos": 393,
+    "NOUN|Foreign=Yes|r-ccomp": 394,
+    "NOUN|Foreign=Yes|r-clf": 395,
+    "NOUN|Foreign=Yes|r-compound": 396,
+    "NOUN|Foreign=Yes|r-conj": 397,
+    "NOUN|Foreign=Yes|r-flat": 398,
+    "NOUN|Foreign=Yes|r-iobj": 399,
+    "NOUN|Foreign=Yes|r-list": 400,
+    "NOUN|Foreign=Yes|r-nmod": 401,
+    "NOUN|Foreign=Yes|r-obj": 402,
+    "NOUN|Foreign=Yes|r-obl": 403,
+    "NOUN|Foreign=Yes|r-xcomp": 404,
+    "NOUN|Foreign=Yes|root": 405,
+    "NOUN|NameType=Com": 406,
+    "NOUN|NameType=Com|r-nmod": 407,
+    "NOUN|NameType=Geo": 408,
+    "NOUN|NameType=Geo|l-nsubj": 409,
+    "NOUN|NameType=Geo|r-nmod": 410,
+    "NOUN|NameType=Geo|r-obj": 411,
+    "NOUN|NameType=Nat": 412,
+    "NOUN|NameType=Nat|r-nmod": 413,
+    "NOUN|NameType=Oth": 414,
+    "NOUN|NameType=Oth|l-nsubj": 415,
+    "NOUN|NameType=Oth|r-conj": 416,
+    "NOUN|NameType=Oth|r-flat": 417,
+    "NOUN|NameType=Oth|r-nmod": 418,
+    "NOUN|NameType=Pro": 419,
+    "NOUN|NameType=Pro|r-nmod": 420,
+    "NOUN|NameType=Prs": 421,
+    "NOUN|NameType=Prs|l-nsubj": 422,
+    "NOUN|NameType=Prs|r-nmod": 423,
+    "NOUN|NounType=Class": 424,
+    "NOUN|NounType=Class|Prefix=Yes": 425,
+    "NOUN|NounType=Class|Prefix=Yes|l-advcl": 426,
+    "NOUN|NounType=Class|Prefix=Yes|l-advmod": 427,
+    "NOUN|NounType=Class|Prefix=Yes|l-mark": 428,
+    "NOUN|NounType=Class|Prefix=Yes|l-nmod": 429,
+    "NOUN|NounType=Class|Prefix=Yes|l-nsubj": 430,
+    "NOUN|NounType=Class|Prefix=Yes|r-advcl": 431,
+    "NOUN|NounType=Class|Prefix=Yes|r-clf": 432,
+    "NOUN|NounType=Class|Prefix=Yes|r-nmod": 433,
+    "NOUN|NounType=Class|Prefix=Yes|r-obj": 434,
+    "NOUN|NounType=Class|l-advcl": 435,
+    "NOUN|NounType=Class|l-advmod": 436,
+    "NOUN|NounType=Class|l-clf": 437,
+    "NOUN|NounType=Class|l-dislocated": 438,
+    "NOUN|NounType=Class|l-nmod": 439,
+    "NOUN|NounType=Class|l-nsubj": 440,
+    "NOUN|NounType=Class|l-obj": 441,
+    "NOUN|NounType=Class|l-obl": 442,
+    "NOUN|NounType=Class|r-acl": 443,
+    "NOUN|NounType=Class|r-advcl": 444,
+    "NOUN|NounType=Class|r-advmod": 445,
+    "NOUN|NounType=Class|r-appos": 446,
+    "NOUN|NounType=Class|r-cc": 447,
+    "NOUN|NounType=Class|r-ccomp": 448,
+    "NOUN|NounType=Class|r-clf": 449,
+    "NOUN|NounType=Class|r-compound": 450,
+    "NOUN|NounType=Class|r-conj": 451,
+    "NOUN|NounType=Class|r-dislocated": 452,
+    "NOUN|NounType=Class|r-fixed": 453,
+    "NOUN|NounType=Class|r-flat": 454,
+    "NOUN|NounType=Class|r-iobj": 455,
+    "NOUN|NounType=Class|r-list": 456,
+    "NOUN|NounType=Class|r-nmod": 457,
+    "NOUN|NounType=Class|r-nummod": 458,
+    "NOUN|NounType=Class|r-obj": 459,
+    "NOUN|NounType=Class|r-obl": 460,
+    "NOUN|NounType=Class|r-orphan": 461,
+    "NOUN|NounType=Class|r-xcomp": 462,
+    "NOUN|NounType=Class|root": 463,
+    "NOUN|NumType=Mult": 464,
+    "NOUN|NumType=Mult|r-advcl": 465,
+    "NOUN|NumType=Mult|r-nmod": 466,
+    "NOUN|NumType=Mult|r-obj": 467,
+    "NOUN|PartType=Enp": 468,
+    "NOUN|PartType=Enp|r-obj": 469,
+    "NOUN|PartType=Enp|r-obl": 470,
+    "NOUN|PartType=Int": 471,
+    "NOUN|PartType=Int|r-obj": 472,
+    "NOUN|PartType=Res": 473,
+    "NOUN|PartType=Res|r-nmod": 474,
+    "NOUN|PartType=Res|r-obj": 475,
+    "NOUN|Prefix=Yes": 476,
+    "NOUN|Prefix=Yes|l-acl": 477,
+    "NOUN|Prefix=Yes|l-advcl": 478,
+    "NOUN|Prefix=Yes|l-clf": 479,
+    "NOUN|Prefix=Yes|l-csubj": 480,
+    "NOUN|Prefix=Yes|l-dislocated": 481,
+    "NOUN|Prefix=Yes|l-flat": 482,
+    "NOUN|Prefix=Yes|l-nmod": 483,
+    "NOUN|Prefix=Yes|l-nsubj": 484,
+    "NOUN|Prefix=Yes|l-obj": 485,
+    "NOUN|Prefix=Yes|l-obl": 486,
+    "NOUN|Prefix=Yes|r-acl": 487,
+    "NOUN|Prefix=Yes|r-advcl": 488,
+    "NOUN|Prefix=Yes|r-advmod": 489,
+    "NOUN|Prefix=Yes|r-appos": 490,
+    "NOUN|Prefix=Yes|r-case": 491,
+    "NOUN|Prefix=Yes|r-cc": 492,
+    "NOUN|Prefix=Yes|r-ccomp": 493,
+    "NOUN|Prefix=Yes|r-clf": 494,
+    "NOUN|Prefix=Yes|r-compound": 495,
+    "NOUN|Prefix=Yes|r-conj": 496,
+    "NOUN|Prefix=Yes|r-dislocated": 497,
+    "NOUN|Prefix=Yes|r-fixed": 498,
+    "NOUN|Prefix=Yes|r-flat": 499,
+    "NOUN|Prefix=Yes|r-iobj": 500,
+    "NOUN|Prefix=Yes|r-list": 501,
+    "NOUN|Prefix=Yes|r-nmod": 502,
+    "NOUN|Prefix=Yes|r-nummod": 503,
+    "NOUN|Prefix=Yes|r-obj": 504,
+    "NOUN|Prefix=Yes|r-obl": 505,
+    "NOUN|Prefix=Yes|r-orphan": 506,
+    "NOUN|Prefix=Yes|r-xcomp": 507,
+    "NOUN|Prefix=Yes|root": 508,
+    "NOUN|l-acl": 509,
+    "NOUN|l-advcl": 510,
+    "NOUN|l-advmod": 511,
+    "NOUN|l-case": 512,
+    "NOUN|l-ccomp": 513,
+    "NOUN|l-compound": 514,
+    "NOUN|l-csubj": 515,
+    "NOUN|l-discourse": 516,
+    "NOUN|l-dislocated": 517,
+    "NOUN|l-expl": 518,
+    "NOUN|l-flat": 519,
+    "NOUN|l-iobj": 520,
+    "NOUN|l-mark": 521,
+    "NOUN|l-nmod": 522,
+    "NOUN|l-nsubj": 523,
+    "NOUN|l-nummod": 524,
+    "NOUN|l-obj": 525,
+    "NOUN|l-obl": 526,
+    "NOUN|l-orphan": 527,
+    "NOUN|l-vocative": 528,
+    "NOUN|r-acl": 529,
+    "NOUN|r-advcl": 530,
+    "NOUN|r-advmod": 531,
+    "NOUN|r-appos": 532,
+    "NOUN|r-case": 533,
+    "NOUN|r-cc": 534,
+    "NOUN|r-ccomp": 535,
+    "NOUN|r-clf": 536,
+    "NOUN|r-compound": 537,
+    "NOUN|r-conj": 538,
+    "NOUN|r-cop": 539,
+    "NOUN|r-discourse": 540,
+    "NOUN|r-dislocated": 541,
+    "NOUN|r-fixed": 542,
+    "NOUN|r-flat": 543,
+    "NOUN|r-iobj": 544,
+    "NOUN|r-list": 545,
+    "NOUN|r-mark": 546,
+    "NOUN|r-nmod": 547,
+    "NOUN|r-nsubj": 548,
+    "NOUN|r-nummod": 549,
+    "NOUN|r-obj": 550,
+    "NOUN|r-obl": 551,
+    "NOUN|r-orphan": 552,
+    "NOUN|r-parataxis": 553,
+    "NOUN|r-xcomp": 554,
+    "NOUN|root": 555,
+    "NUM": 556,
+    "NUM|Abbr=Yes": 557,
+    "NUM|Abbr=Yes|r-flat": 558,
+    "NUM|Abbr=Yes|r-nummod": 559,
+    "NUM|Abbr=Yes|r-obj": 560,
+    "NUM|Foreign=Yes": 561,
+    "NUM|Foreign=Yes|r-clf": 562,
+    "NUM|NumType=Mult": 563,
+    "NUM|NumType=Mult|l-advmod": 564,
+    "NUM|NumType=Mult|l-nummod": 565,
+    "NUM|NumType=Mult|r-advmod": 566,
+    "NUM|Prefix=Yes": 567,
+    "NUM|Prefix=Yes|l-nummod": 568,
+    "NUM|l-advcl": 569,
+    "NUM|l-advmod": 570,
+    "NUM|l-case": 571,
+    "NUM|l-clf": 572,
+    "NUM|l-dep": 573,
+    "NUM|l-flat": 574,
+    "NUM|l-nmod": 575,
+    "NUM|l-nsubj": 576,
+    "NUM|l-nummod": 577,
+    "NUM|l-obl": 578,
+    "NUM|r-acl": 579,
+    "NUM|r-advmod": 580,
+    "NUM|r-appos": 581,
+    "NUM|r-ccomp": 582,
+    "NUM|r-compound": 583,
+    "NUM|r-conj": 584,
+    "NUM|r-det": 585,
+    "NUM|r-fixed": 586,
+    "NUM|r-flat": 587,
+    "NUM|r-iobj": 588,
+    "NUM|r-nmod": 589,
+    "NUM|r-nummod": 590,
+    "NUM|r-obj": 591,
+    "NUM|r-obl": 592,
+    "NUM|root": 593,
+    "PART": 594,
+    "PART|NameType=Oth": 595,
+    "PART|NameType=Oth|l-advmod": 596,
+    "PART|NounType=Class|PartType=Emp": 597,
+    "PART|NounType=Class|PartType=Emp|Prefix=Yes": 598,
+    "PART|NounType=Class|PartType=Emp|Prefix=Yes|l-mark": 599,
+    "PART|NounType=Class|PartType=Emp|l-mark": 600,
+    "PART|NounType=Class|Prefix=Yes": 601,
+    "PART|NounType=Class|Prefix=Yes|l-mark": 602,
+    "PART|NumType=Mult|PartType=Emp": 603,
+    "PART|NumType=Mult|PartType=Emp|l-mark": 604,
+    "PART|PartType=Adj": 605,
+    "PART|PartType=Adj|l-mark": 606,
+    "PART|PartType=Adj|l-orphan": 607,
+    "PART|PartType=Adj|r-acl": 608,
+    "PART|PartType=Adj|r-compound": 609,
+    "PART|PartType=Adj|r-nmod": 610,
+    "PART|PartType=Adv": 611,
+    "PART|PartType=Adv|l-advmod": 612,
+    "PART|PartType=Adv|l-mark": 613,
+    "PART|PartType=Adv|r-advmod": 614,
+    "PART|PartType=Emp": 615,
+    "PART|PartType=Emp|Prefix=Yes": 616,
+    "PART|PartType=Emp|Prefix=Yes|l-advmod": 617,
+    "PART|PartType=Emp|Prefix=Yes|l-aux": 618,
+    "PART|PartType=Emp|Prefix=Yes|l-mark": 619,
+    "PART|PartType=Emp|l-advmod": 620,
+    "PART|PartType=Emp|l-case": 621,
+    "PART|PartType=Emp|l-discourse": 622,
+    "PART|PartType=Emp|l-mark": 623,
+    "PART|PartType=Emp|r-acl": 624,
+    "PART|PartType=Emp|r-advmod": 625,
+    "PART|PartType=Emp|r-aux": 626,
+    "PART|PartType=Emp|r-compound": 627,
+    "PART|PartType=Emp|r-det": 628,
+    "PART|PartType=Emp|r-fixed": 629,
+    "PART|PartType=Emp|r-mark": 630,
+    "PART|PartType=Emp|r-nmod": 631,
+    "PART|PartType=Enp": 632,
+    "PART|PartType=Enp|l-discourse": 633,
+    "PART|PartType=Enp|r-acl": 634,
+    "PART|PartType=Enp|r-advmod": 635,
+    "PART|PartType=Enp|r-compound": 636,
+    "PART|PartType=Enp|r-dep": 637,
+    "PART|PartType=Enp|r-det": 638,
+    "PART|PartType=Enp|r-discourse": 639,
+    "PART|PartType=Enp|r-fixed": 640,
+    "PART|PartType=Enp|r-obl": 641,
+    "PART|PartType=Int": 642,
+    "PART|PartType=Int|l-advmod": 643,
+    "PART|PartType=Int|l-mark": 644,
+    "PART|PartType=Int|r-acl": 645,
+    "PART|PartType=Int|r-advmod": 646,
+    "PART|PartType=Int|r-dep": 647,
+    "PART|PartType=Int|r-discourse": 648,
+    "PART|PartType=Int|r-nmod": 649,
+    "PART|PartType=Int|r-obj": 650,
+    "PART|PartType=Int|r-obl": 651,
+    "PART|PartType=Neg": 652,
+    "PART|PartType=Neg|l-advcl": 653,
+    "PART|PartType=Neg|l-advmod": 654,
+    "PART|PartType=Neg|l-aux": 655,
+    "PART|PartType=Neg|l-mark": 656,
+    "PART|PartType=Neg|r-acl": 657,
+    "PART|PartType=Neg|r-advmod": 658,
+    "PART|PartType=Neg|r-fixed": 659,
+    "PART|PartType=Res": 660,
+    "PART|PartType=Res|r-advmod": 661,
+    "PART|PartType=Res|r-discourse": 662,
+    "PART|PartType=Res|r-fixed": 663,
+    "PART|Prefix=Yes": 664,
+    "PART|Prefix=Yes|l-advmod": 665,
+    "PART|Prefix=Yes|l-aux": 666,
+    "PART|Prefix=Yes|l-mark": 667,
+    "PART|Prefix=Yes|r-acl": 668,
+    "PART|Prefix=Yes|r-nmod": 669,
+    "PART|l-advmod": 670,
+    "PART|l-discourse": 671,
+    "PART|l-mark": 672,
+    "PART|l-nsubj": 673,
+    "PART|r-acl": 674,
+    "PART|r-advmod": 675,
+    "PART|r-discourse": 676,
+    "PART|r-fixed": 677,
+    "PART|r-mark": 678,
+    "PART|r-obj": 679,
+    "PRON": 680,
+    "PRON|NounType=Class": 681,
+    "PRON|NounType=Class|r-clf": 682,
+    "PRON|PronType=Prs": 683,
+    "PRON|PronType=Prs|l-advmod": 684,
+    "PRON|PronType=Prs|l-expl": 685,
+    "PRON|PronType=Prs|l-nsubj": 686,
+    "PRON|PronType=Prs|l-obj": 687,
+    "PRON|PronType=Prs|l-obl": 688,
+    "PRON|PronType=Prs|r-advcl": 689,
+    "PRON|PronType=Prs|r-advmod": 690,
+    "PRON|PronType=Prs|r-ccomp": 691,
+    "PRON|PronType=Prs|r-clf": 692,
+    "PRON|PronType=Prs|r-conj": 693,
+    "PRON|PronType=Prs|r-nmod": 694,
+    "PRON|PronType=Prs|r-nsubj": 695,
+    "PRON|PronType=Prs|r-obj": 696,
+    "PRON|PronType=Prs|r-obl": 697,
+    "PRON|PronType=Prs|root": 698,
+    "PRON|PronType=Rcp": 699,
+    "PRON|PronType=Rcp|r-advmod": 700,
+    "PRON|PronType=Rcp|r-iobj": 701,
+    "PRON|PronType=Rcp|r-nmod": 702,
+    "PRON|PronType=Rcp|r-obj": 703,
+    "PRON|PronType=Rcp|r-obl": 704,
+    "PRON|l-advcl": 705,
+    "PRON|l-advmod": 706,
+    "PRON|l-compound": 707,
+    "PRON|l-csubj": 708,
+    "PRON|l-dislocated": 709,
+    "PRON|l-expl": 710,
+    "PRON|l-iobj": 711,
+    "PRON|l-mark": 712,
+    "PRON|l-nsubj": 713,
+    "PRON|l-obj": 714,
+    "PRON|l-obl": 715,
+    "PRON|r-acl": 716,
+    "PRON|r-advmod": 717,
+    "PRON|r-appos": 718,
+    "PRON|r-ccomp": 719,
+    "PRON|r-compound": 720,
+    "PRON|r-conj": 721,
+    "PRON|r-det": 722,
+    "PRON|r-discourse": 723,
+    "PRON|r-fixed": 724,
+    "PRON|r-flat": 725,
+    "PRON|r-iobj": 726,
+    "PRON|r-nmod": 727,
+    "PRON|r-nsubj": 728,
+    "PRON|r-obj": 729,
+    "PRON|r-obl": 730,
+    "PROPN": 731,
+    "PROPN|Abbr=Yes": 732,
+    "PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth": 733,
+    "PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth|r-obj": 734,
+    "PROPN|Abbr=Yes|NameType=Com": 735,
+    "PROPN|Abbr=Yes|NameType=Com|r-advmod": 736,
+    "PROPN|Abbr=Yes|NameType=Com|r-nmod": 737,
+    "PROPN|Abbr=Yes|l-nmod": 738,
+    "PROPN|Abbr=Yes|l-nsubj": 739,
+    "PROPN|Abbr=Yes|r-nmod": 740,
+    "PROPN|Foreign=Yes": 741,
+    "PROPN|Foreign=Yes|NameType=Com": 742,
+    "PROPN|Foreign=Yes|NameType=Com|l-nsubj": 743,
+    "PROPN|Foreign=Yes|NameType=Com|r-list": 744,
+    "PROPN|Foreign=Yes|NameType=Com|r-nmod": 745,
+    "PROPN|Foreign=Yes|NameType=Com|r-obl": 746,
+    "PROPN|Foreign=Yes|NameType=Geo": 747,
+    "PROPN|Foreign=Yes|NameType=Geo|r-obj": 748,
+    "PROPN|Foreign=Yes|NameType=Geo|r-obl": 749,
+    "PROPN|Foreign=Yes|NameType=Giv": 750,
+    "PROPN|Foreign=Yes|NameType=Giv|l-nsubj": 751,
+    "PROPN|Foreign=Yes|NameType=Oth": 752,
+    "PROPN|Foreign=Yes|NameType=Oth|r-conj": 753,
+    "PROPN|Foreign=Yes|NameType=Oth|r-flat": 754,
+    "PROPN|Foreign=Yes|NameType=Oth|r-nmod": 755,
+    "PROPN|Foreign=Yes|NameType=Prs": 756,
+    "PROPN|Foreign=Yes|NameType=Prs|l-flat": 757,
+    "PROPN|Foreign=Yes|NameType=Prs|l-nsubj": 758,
+    "PROPN|Foreign=Yes|NameType=Prs|r-conj": 759,
+    "PROPN|Foreign=Yes|NameType=Prs|r-flat": 760,
+    "PROPN|Foreign=Yes|NameType=Prs|r-nmod": 761,
+    "PROPN|Foreign=Yes|NameType=Prs|r-obj": 762,
+    "PROPN|Foreign=Yes|NameType=Prs|r-obl": 763,
+    "PROPN|Foreign=Yes|NameType=Sur": 764,
+    "PROPN|Foreign=Yes|NameType=Sur|r-flat": 765,
+    "PROPN|Foreign=Yes|l-flat": 766,
+    "PROPN|Foreign=Yes|l-nmod": 767,
+    "PROPN|Foreign=Yes|l-nsubj": 768,
+    "PROPN|Foreign=Yes|l-obl": 769,
+    "PROPN|Foreign=Yes|r-appos": 770,
+    "PROPN|Foreign=Yes|r-ccomp": 771,
+    "PROPN|Foreign=Yes|r-compound": 772,
+    "PROPN|Foreign=Yes|r-conj": 773,
+    "PROPN|Foreign=Yes|r-flat": 774,
+    "PROPN|Foreign=Yes|r-iobj": 775,
+    "PROPN|Foreign=Yes|r-list": 776,
+    "PROPN|Foreign=Yes|r-nmod": 777,
+    "PROPN|Foreign=Yes|r-nsubj": 778,
+    "PROPN|Foreign=Yes|r-obj": 779,
+    "PROPN|Foreign=Yes|r-obl": 780,
+    "PROPN|Foreign=Yes|root": 781,
+    "PROPN|NameType=Com": 782,
+    "PROPN|NameType=Com|l-nsubj": 783,
+    "PROPN|NameType=Com|l-obl": 784,
+    "PROPN|NameType=Com|r-appos": 785,
+    "PROPN|NameType=Com|r-conj": 786,
+    "PROPN|NameType=Com|r-flat": 787,
+    "PROPN|NameType=Com|r-list": 788,
+    "PROPN|NameType=Com|r-nmod": 789,
+    "PROPN|NameType=Com|r-nsubj": 790,
+    "PROPN|NameType=Com|r-obj": 791,
+    "PROPN|NameType=Com|r-obl": 792,
+    "PROPN|NameType=Geo": 793,
+    "PROPN|NameType=Geo|l-nsubj": 794,
+    "PROPN|NameType=Geo|l-obl": 795,
+    "PROPN|NameType=Geo|r-compound": 796,
+    "PROPN|NameType=Geo|r-conj": 797,
+    "PROPN|NameType=Geo|r-flat": 798,
+    "PROPN|NameType=Geo|r-list": 799,
+    "PROPN|NameType=Geo|r-nmod": 800,
+    "PROPN|NameType=Geo|r-nsubj": 801,
+    "PROPN|NameType=Geo|r-nummod": 802,
+    "PROPN|NameType=Geo|r-obj": 803,
+    "PROPN|NameType=Geo|r-obl": 804,
+    "PROPN|NameType=Geo|root": 805,
+    "PROPN|NameType=Giv": 806,
+    "PROPN|NameType=Giv|l-dislocated": 807,
+    "PROPN|NameType=Giv|l-nsubj": 808,
+    "PROPN|NameType=Giv|l-obl": 809,
+    "PROPN|NameType=Giv|r-acl": 810,
+    "PROPN|NameType=Giv|r-appos": 811,
+    "PROPN|NameType=Giv|r-ccomp": 812,
+    "PROPN|NameType=Giv|r-conj": 813,
+    "PROPN|NameType=Giv|r-flat": 814,
+    "PROPN|NameType=Giv|r-list": 815,
+    "PROPN|NameType=Giv|r-nmod": 816,
+    "PROPN|NameType=Giv|r-nsubj": 817,
+    "PROPN|NameType=Giv|r-obj": 818,
+    "PROPN|NameType=Giv|r-obl": 819,
+    "PROPN|NameType=Giv|root": 820,
+    "PROPN|NameType=Nat": 821,
+    "PROPN|NameType=Nat|l-csubj": 822,
+    "PROPN|NameType=Nat|l-nsubj": 823,
+    "PROPN|NameType=Nat|l-obl": 824,
+    "PROPN|NameType=Nat|r-acl": 825,
+    "PROPN|NameType=Nat|r-appos": 826,
+    "PROPN|NameType=Nat|r-compound": 827,
+    "PROPN|NameType=Nat|r-conj": 828,
+    "PROPN|NameType=Nat|r-flat": 829,
+    "PROPN|NameType=Nat|r-list": 830,
+    "PROPN|NameType=Nat|r-nmod": 831,
+    "PROPN|NameType=Nat|r-nummod": 832,
+    "PROPN|NameType=Nat|r-obj": 833,
+    "PROPN|NameType=Nat|r-obl": 834,
+    "PROPN|NameType=Oth": 835,
+    "PROPN|NameType=Oth|l-dislocated": 836,
+    "PROPN|NameType=Oth|l-nsubj": 837,
+    "PROPN|NameType=Oth|r-acl": 838,
+    "PROPN|NameType=Oth|r-appos": 839,
+    "PROPN|NameType=Oth|r-compound": 840,
+    "PROPN|NameType=Oth|r-conj": 841,
+    "PROPN|NameType=Oth|r-flat": 842,
+    "PROPN|NameType=Oth|r-nmod": 843,
+    "PROPN|NameType=Oth|r-obj": 844,
+    "PROPN|NameType=Oth|r-obl": 845,
+    "PROPN|NameType=Oth|root": 846,
+    "PROPN|NameType=Pro": 847,
+    "PROPN|NameType=Pro|l-nsubj": 848,
+    "PROPN|NameType=Pro|l-obl": 849,
+    "PROPN|NameType=Pro|r-advcl": 850,
+    "PROPN|NameType=Pro|r-flat": 851,
+    "PROPN|NameType=Pro|r-nmod": 852,
+    "PROPN|NameType=Pro|r-obj": 853,
+    "PROPN|NameType=Prs": 854,
+    "PROPN|NameType=Prs|l-dislocated": 855,
+    "PROPN|NameType=Prs|l-nsubj": 856,
+    "PROPN|NameType=Prs|l-obl": 857,
+    "PROPN|NameType=Prs|l-vocative": 858,
+    "PROPN|NameType=Prs|r-conj": 859,
+    "PROPN|NameType=Prs|r-discourse": 860,
+    "PROPN|NameType=Prs|r-flat": 861,
+    "PROPN|NameType=Prs|r-list": 862,
+    "PROPN|NameType=Prs|r-nmod": 863,
+    "PROPN|NameType=Prs|r-obj": 864,
+    "PROPN|NameType=Prs|r-obl": 865,
+    "PROPN|NameType=Prs|r-vocative": 866,
+    "PROPN|NameType=Sur": 867,
+    "PROPN|NameType=Sur|l-nsubj": 868,
+    "PROPN|NameType=Sur|r-flat": 869,
+    "PROPN|NameType=Sur|r-nmod": 870,
+    "PROPN|NounType=Class": 871,
+    "PROPN|NounType=Class|r-clf": 872,
+    "PROPN|Prefix=Yes": 873,
+    "PROPN|Prefix=Yes|l-nsubj": 874,
+    "PROPN|Prefix=Yes|r-nmod": 875,
+    "PROPN|l-advmod": 876,
+    "PROPN|l-nsubj": 877,
+    "PROPN|l-obl": 878,
+    "PROPN|r-acl": 879,
+    "PROPN|r-advmod": 880,
+    "PROPN|r-appos": 881,
+    "PROPN|r-clf": 882,
+    "PROPN|r-compound": 883,
+    "PROPN|r-conj": 884,
+    "PROPN|r-fixed": 885,
+    "PROPN|r-flat": 886,
+    "PROPN|r-iobj": 887,
+    "PROPN|r-list": 888,
+    "PROPN|r-nmod": 889,
+    "PROPN|r-obj": 890,
+    "PROPN|r-obl": 891,
+    "PROPN|root": 892,
+    "PUNCT": 893,
+    "PUNCT|NounType=Class": 894,
+    "PUNCT|NounType=Class|r-punct": 895,
+    "PUNCT|l-advmod": 896,
+    "PUNCT|l-dep": 897,
+    "PUNCT|l-punct": 898,
+    "PUNCT|r-dep": 899,
+    "PUNCT|r-punct": 900,
+    "SCONJ": 901,
+    "SCONJ|NumType=Mult": 902,
+    "SCONJ|NumType=Mult|l-mark": 903,
+    "SCONJ|Prefix=Yes": 904,
+    "SCONJ|Prefix=Yes|l-cc": 905,
+    "SCONJ|Prefix=Yes|l-mark": 906,
+    "SCONJ|VerbType=Cop": 907,
+    "SCONJ|VerbType=Cop|l-mark": 908,
+    "SCONJ|l-advmod": 909,
+    "SCONJ|l-case": 910,
+    "SCONJ|l-cc": 911,
+    "SCONJ|l-discourse": 912,
+    "SCONJ|l-mark": 913,
+    "SCONJ|l-nsubj": 914,
+    "SCONJ|l-orphan": 915,
+    "SCONJ|r-advcl": 916,
+    "SCONJ|r-compound": 917,
+    "SCONJ|r-fixed": 918,
+    "SCONJ|r-flat": 919,
+    "SCONJ|r-mark": 920,
+    "SCONJ|r-orphan": 921,
+    "SCONJ|root": 922,
+    "SYM": 923,
+    "SYM|l-dep": 924,
+    "SYM|r-clf": 925,
+    "SYM|r-nmod": 926,
+    "SYM|r-obj": 927,
+    "SYM|r-obl": 928,
+    "SYM|r-xcomp": 929,
+    "VERB": 930,
+    "VERB|Abbr=Yes": 931,
+    "VERB|Abbr=Yes|r-acl": 932,
+    "VERB|Foreign=Yes": 933,
+    "VERB|Foreign=Yes|l-nsubj": 934,
+    "VERB|Foreign=Yes|r-acl": 935,
+    "VERB|Foreign=Yes|r-advcl": 936,
+    "VERB|Foreign=Yes|r-ccomp": 937,
+    "VERB|Foreign=Yes|r-compound": 938,
+    "VERB|Foreign=Yes|r-conj": 939,
+    "VERB|Foreign=Yes|r-flat": 940,
+    "VERB|Foreign=Yes|r-nmod": 941,
+    "VERB|Foreign=Yes|r-xcomp": 942,
+    "VERB|Foreign=Yes|root": 943,
+    "VERB|NounType=Class": 944,
+    "VERB|NounType=Class|r-acl": 945,
+    "VERB|NounType=Class|r-compound": 946,
+    "VERB|PartType=Adj": 947,
+    "VERB|PartType=Adj|r-acl": 948,
+    "VERB|Prefix=Yes": 949,
+    "VERB|Prefix=Yes|l-acl": 950,
+    "VERB|Prefix=Yes|l-nsubj": 951,
+    "VERB|Prefix=Yes|r-acl": 952,
+    "VERB|Prefix=Yes|r-advcl": 953,
+    "VERB|Prefix=Yes|r-ccomp": 954,
+    "VERB|Prefix=Yes|r-compound": 955,
+    "VERB|Prefix=Yes|r-conj": 956,
+    "VERB|Prefix=Yes|r-parataxis": 957,
+    "VERB|Prefix=Yes|root": 958,
+    "VERB|VerbType=Cop": 959,
+    "VERB|VerbType=Cop|l-advmod": 960,
+    "VERB|VerbType=Cop|l-cop": 961,
+    "VERB|VerbType=Cop|r-acl": 962,
+    "VERB|VerbType=Cop|r-advcl": 963,
+    "VERB|VerbType=Cop|r-ccomp": 964,
+    "VERB|VerbType=Cop|r-compound": 965,
+    "VERB|VerbType=Cop|r-parataxis": 966,
+    "VERB|VerbType=Cop|root": 967,
+    "VERB|l-acl": 968,
+    "VERB|l-advcl": 969,
+    "VERB|l-advmod": 970,
+    "VERB|l-aux": 971,
+    "VERB|l-case": 972,
+    "VERB|l-cc": 973,
+    "VERB|l-ccomp": 974,
+    "VERB|l-compound": 975,
+    "VERB|l-conj": 976,
+    "VERB|l-cop": 977,
+    "VERB|l-csubj": 978,
+    "VERB|l-discourse": 979,
+    "VERB|l-dislocated": 980,
+    "VERB|l-mark": 981,
+    "VERB|l-nsubj": 982,
+    "VERB|l-obl": 983,
+    "VERB|l-orphan": 984,
+    "VERB|l-xcomp": 985,
+    "VERB|r-acl": 986,
+    "VERB|r-advcl": 987,
+    "VERB|r-advmod": 988,
+    "VERB|r-appos": 989,
+    "VERB|r-aux": 990,
+    "VERB|r-case": 991,
+    "VERB|r-cc": 992,
+    "VERB|r-ccomp": 993,
+    "VERB|r-clf": 994,
+    "VERB|r-compound": 995,
+    "VERB|r-conj": 996,
+    "VERB|r-dep": 997,
+    "VERB|r-det": 998,
+    "VERB|r-discourse": 999,
+    "VERB|r-fixed": 1000,
+    "VERB|r-flat": 1001,
+    "VERB|r-list": 1002,
+    "VERB|r-mark": 1003,
+    "VERB|r-nmod": 1004,
+    "VERB|r-nsubj": 1005,
+    "VERB|r-obj": 1006,
+    "VERB|r-obl": 1007,
+    "VERB|r-orphan": 1008,
+    "VERB|r-parataxis": 1009,
+    "VERB|r-punct": 1010,
+    "VERB|r-xcomp": 1011,
+    "VERB|root": 1012
+  },
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

maker.py

@@ -0,0 +1,116 @@
+#! /usr/bin/python3
+src="meta-llama/Llama-3.2-1B"
+tgt="KoichiYasuoka/Llama-3.2-1B-thai-ud-causal"
+url="https://github.com/KoichiYasuoka/spaCy-Thai"
+import os
+d=os.path.basename(url)
+os.system("test -d "+d+" || git clone --depth=1 "+url)
+os.system("for F in train dev test ; do cp "+d+"/UD_Thai-Corpora/th_tud-ud-$F.conllu $F.conllu ; done")
+class UDCausalDataset(object):
+  def __init__(self,conllu,tokenizer,oldtokenizer=None,embeddings=None):
+    self.conllu=open(conllu,"r",encoding="utf-8")
+    self.tokenizer=tokenizer
+    self.oldtokenizer=oldtokenizer if oldtokenizer else tokenizer
+    self.embeddings=embeddings
+    self.max_tokens=3
+    self.seeks=[(0,0)]
+    label=set(["SYM"])
+    dep=set()
+    s=self.conllu.readline()
+    while s!="":
+      if s=="\n":
+        self.seeks.append((self.conllu.tell(),0))
+      else:
+        w=s.split("\t")
+        if len(w)==10:
+          if w[0].isdecimal():
+            p=w[3] if w[5]=="_" else w[3]+"|"+w[5]
+            label.add(p)
+            dep.add(p+("|" if w[6]=="0" else "|l-" if int(w[0])<int(w[6]) else "|r-")+w[7])
+            self.seeks.append((self.seeks[-1][0],int(w[0])))
+            self.max_tokens=max(self.max_tokens,int(w[0])*2+1)
+      s=self.conllu.readline()
+    lid={}
+    for i,l in enumerate(sorted(label)):
+      lid[l],lid["B-"+l],lid["I-"+l]=i*3,i*3+1,i*3+2
+    for i,d in enumerate(sorted(dep),len(lid)):
+      lid[d]=i
+    self.label2id=lid
+  def __call__(*args):
+    lid={l:i for i,l in enumerate(sorted(set(sum([list(t.label2id) for t in args],[]))))}
+    for t in args:
+      t.label2id=lid
+    return lid
+  def __del__(self):
+    self.conllu.close()
+  __len__=lambda self:len(self.seeks)-1
+  def __getitem__(self,i):
+    s,t=self.seeks[i]
+    self.conllu.seek(s)
+    form,upos,deps,w=[],[],[],[""]
+    while w[0]!="\n":
+      w=self.conllu.readline().split("\t")
+      if len(w)==10:
+        form.append(w[1])
+        if w[0].isdecimal():
+          upos.append(w[3] if w[5]=="_" else w[3]+"|"+w[5])
+          deps.append((int(w[6]),w[7]))
+    if t==0:
+      v=self.tokenizer(form,add_special_tokens=False)
+      i,u=[self.tokenizer.cls_token_id],["SYM"]
+      for j,(x,y) in enumerate(zip(v["input_ids"],upos)):
+        if x!=[]:
+          i+=x
+          u+=[y] if len(x)==1 else ["B-"+y]+["I-"+y]*(len(x)-1)
+      emb=self.embeddings
+      pad=self.tokenizer.pad_token_id
+    else:
+      import torch
+      v=self.oldtokenizer(form,add_special_tokens=False)
+      m=[]
+      for x in v["input_ids"]:
+        if x==[]:
+          m.append(self.embeddings[self.tokenizer.unk_token_id,:])
+        else:
+          m.append(self.embeddings[x,:].sum(axis=0))
+      m.append(self.embeddings[self.tokenizer.sep_token_id,:])
+      m.append(self.embeddings[self.tokenizer.pad_token_id,:])
+      m.append(self.embeddings[self.tokenizer.cls_token_id,:])
+      emb=torch.stack(m)
+      i,u=list(range(-1,len(upos)+1)),["SYM"]+upos+["SYM"]
+      i.append(t-1)
+      k,d=deps[t-1]
+      u.append(upos[t-1]+"|"+d if k==0 else upos[t-1])
+      for j in range(t,len(upos)):
+        i.append(j)
+        a,b=deps[j]
+        u.append(upos[j]+"|r-"+b if a==t else upos[t-1]+"|l-"+d if j+1==k else upos[j])
+      pad=-1
+    j=self.max_tokens-len(i)
+    if j>0:
+      ids=i+[pad]*j
+      upos=u+["SYM"]*j
+    else:
+      ids=i[0:self.max_tokens]
+      upos=u[0:self.max_tokens]
+    return {"inputs_embeds":emb[ids,:],"labels":[self.label2id[p] for p in upos]}
+from transformers import AutoTokenizer,AutoConfig,AutoModelForTokenClassification,DefaultDataCollator,TrainingArguments,Trainer
+from tokenizers.pre_tokenizers import Sequence,Split,Whitespace
+from tokenizers import Regex
+from copy import deepcopy
+otk=AutoTokenizer.from_pretrained(src,cls_token="<|begin_of_text|>",sep_token="<|end_of_text|>",pad_token="<|finetune_right_pad_id|>",unk_token="<|python_tag|>")
+ntk=deepcopy(otk)
+ntk.backend_tokenizer.pre_tokenizer=Sequence([Whitespace(),Split(Regex("[\u0e40-\u0e44]?[\u0e01-\u0e2e][\u0e30-\u0e3a\u0e45\u0e47-\u0e4e]*|."),"isolated"),otk.backend_tokenizer.pre_tokenizer])
+trainDS=UDCausalDataset("train.conllu",ntk,otk)
+devDS=UDCausalDataset("dev.conllu",ntk,otk)
+testDS=UDCausalDataset("test.conllu",ntk,otk)
+lid=trainDS(devDS,testDS)
+cfg=AutoConfig.from_pretrained(src,num_labels=len(lid),label2id=lid,id2label={i:l for l,i in lid.items()},ignore_mismatched_sizes=True)
+mdl=AutoModelForTokenClassification.from_pretrained(src,config=cfg,ignore_mismatched_sizes=True)
+trainDS.embeddings=mdl.get_input_embeddings().weight
+trainDS.max_tokens=min(trainDS.max_tokens,cfg.max_position_embeddings)
+arg=TrainingArguments(num_train_epochs=3,per_device_train_batch_size=16,dataloader_pin_memory=False,output_dir=tgt,overwrite_output_dir=True,save_total_limit=2,learning_rate=5e-05,warmup_ratio=0.1,save_safetensors=False)
+trn=Trainer(args=arg,data_collator=DefaultDataCollator(),model=mdl,train_dataset=trainDS)
+trn.train()
+trn.save_model(tgt)
+otk.save_pretrained(tgt)

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b13a66ff2f2ba35acbe033aae9dd8d94a8a934b09435678299a2c94c6bb93b40
+size 4951610394

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|python_tag|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<|begin_of_text|>",
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "sep_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|python_tag|>"
+}

ud.py

@@ -0,0 +1,147 @@
+import numpy
+from transformers import TokenClassificationPipeline
+
+class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
+  def __init__(self,**kwargs):
+    from copy import deepcopy
+    from tokenizers.pre_tokenizers import Sequence,Split,Whitespace
+    from tokenizers import Regex
+    super().__init__(**kwargs)
+    self.oldtokenizer=deepcopy(self.tokenizer)
+    self.tokenizer.backend_tokenizer.pre_tokenizer=Sequence([Whitespace(),Split(Regex("[\u0e40-\u0e44]?[\u0e01-\u0e2e][\u0e30-\u0e3a\u0e45\u0e47-\u0e4e]*|."),"isolated"),self.oldtokenizer.backend_tokenizer.pre_tokenizer])
+    x=self.model.config.label2id
+    y=[k for k in x if k.startswith("B-") or not (k.startswith("I-") or k.endswith("|root") or k.find("|l-")>0 or k.find("|r-")>0)]
+    self.transition=numpy.full((len(x),len(x)),numpy.nan)
+    for k,v in x.items():
+      for j in ["I-"+k[2:]] if k.startswith("B-") else [k]+y if k.startswith("I-") else y:
+        self.transition[v,x[j]]=0
+  def check_model_type(self,supported_models):
+    pass
+  def postprocess(self,model_outputs,**kwargs):
+    if "logits" not in model_outputs:
+      return self.postprocess(model_outputs[0],**kwargs)
+    m=model_outputs["logits"][0].numpy()
+    e=numpy.exp(m-numpy.max(m,axis=-1,keepdims=True))
+    z=e/e.sum(axis=-1,keepdims=True)
+    for i in range(m.shape[0]-1,0,-1):
+      m[i-1]+=numpy.nanmax(m[i]+self.transition,axis=1)
+    k=[numpy.nanargmax(m[0]+self.transition[0])]
+    for i in range(1,m.shape[0]):
+      k.append(numpy.nanargmax(m[i]+self.transition[k[-1]]))
+    w=[{"entity":self.model.config.id2label[j],"start":s,"end":e,"score":z[i,j]} for i,((s,e),j) in enumerate(zip(model_outputs["offset_mapping"][0].tolist(),k)) if s<e]
+    if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none":
+      for i,t in reversed(list(enumerate(w))):
+        p=t.pop("entity")
+        if p.startswith("I-"):
+          w[i-1]["score"]=min(w[i-1]["score"],t["score"])
+          w[i-1]["end"]=w.pop(i)["end"]
+        elif p.startswith("B-"):
+          t["entity_group"]=p[2:]
+        else:
+          t["entity_group"]=p
+    for t in w:
+      t["text"]=model_outputs["sentence"][t["start"]:t["end"]]
+    return w
+
+class UniversalDependenciesCausalPipeline(BellmanFordTokenClassificationPipeline):
+  def __init__(self,**kwargs):
+    kwargs["aggregation_strategy"]="simple"
+    super().__init__(**kwargs)
+    x=self.model.config.label2id
+    self.root=numpy.full((len(x)),numpy.nan)
+    self.left_arc=numpy.full((len(x)),numpy.nan)
+    self.right_arc=numpy.full((len(x)),numpy.nan)
+    for k,v in x.items():
+      if k.endswith("|root"):
+        self.root[v]=0
+      elif k.find("|l-")>0:
+        self.left_arc[v]=0
+      elif k.find("|r-")>0:
+        self.right_arc[v]=0
+  def postprocess(self,model_outputs,**kwargs):
+    import torch
+    if "logits" not in model_outputs:
+      return self.postprocess(model_outputs[0],**kwargs)
+    m=model_outputs["logits"][0].numpy()
+    for i in range(m.shape[0]-1,0,-1):
+      m[i-1]+=numpy.nanmax(m[i]+self.transition,axis=1)
+    k=[numpy.nanargmax(m[0]+self.transition[0])]
+    for i in range(1,m.shape[0]):
+      k.append(numpy.nanargmax(m[i]+self.transition[k[-1]]))
+    w=[{"entity":self.model.config.id2label[j],"start":s,"end":e} for i,((s,e),j) in enumerate(zip(model_outputs["offset_mapping"][0].tolist(),k)) if s<e]
+    for i,t in reversed(list(enumerate(w))):
+      p=t.pop("entity")
+      if p.startswith("I-"):
+        w[i-1]["end"]=max(w.pop(i)["end"],w[i-1]["end"])
+      elif i>0 and w[i-1]["end"]>w[i]["start"]:
+        w[i-1]["end"]=max(w.pop(i)["end"],w[i-1]["end"])
+      elif p.startswith("B-"):
+        t["entity_group"]=p[2:]
+      else:
+        t["entity_group"]=p
+    d=[model_outputs["sentence"][t["start"]:t["end"]] for t in w]
+    for i in range(len(d)-1,-1,-1):
+      if d[i].startswith(" "):
+        j=len(d[i])-len(d[i].lstrip())
+        d[i]=d[i].lstrip()
+        w[i]["start"]+=j
+      if d[i].endswith(" "):
+        j=len(d[i])-len(d[i].rstrip())
+        d[i]=d[i].rstrip()
+        w[i]["end"]-=j
+      if d[i].strip()=="":
+        d.pop(i)
+        w.pop(i)
+    v=self.oldtokenizer(d,add_special_tokens=False)
+    e=self.model.get_input_embeddings().weight
+    m=[]
+    for x in v["input_ids"]:
+      if x==[]:
+        x=[self.tokenizer.unk_token_id]
+      m.append(e[x,:].sum(axis=0))
+    m.append(e[self.tokenizer.sep_token_id,:])
+    m.append(e[self.tokenizer.pad_token_id,:])
+    m.append(e[self.tokenizer.cls_token_id,:])
+    m=torch.stack(m).to(self.device)
+    k=list(range(-1,len(d)+1))
+    e=[]
+    with torch.no_grad():
+      for i in range(len(d)):
+        e.append(self.model(inputs_embeds=torch.unsqueeze(m[k+list(range(i,len(d)))+[-2]*i,:],0)).logits[0,-len(d):,:])
+    e=torch.stack(e).cpu().numpy()
+    for i in range(len(d)):
+      for j in range(i):
+        e[-j-1,-i-1],e[-i-1,-j-1]=e[-i-1,i-j]+self.left_arc,e[-i-1,i-j]+self.right_arc
+      e[-i-1,-i-1]=e[-i-1,0]+self.root
+    m,p=numpy.nanmax(e,axis=2),numpy.nanargmax(e,axis=2)
+    h=self.chu_liu_edmonds(m)
+    z=[i for i,j in enumerate(h) if i==j]
+    if len(z)>1:
+      k,h=z[numpy.nanargmax(m[z,z])],numpy.nanmin(m)-numpy.nanmax(m)
+      m[:,z]+=[[0 if j in z and (i!=j or i==k) else h for i in z] for j in range(m.shape[0])]
+      h=self.chu_liu_edmonds(m)
+    q=[self.model.config.id2label[p[j,i]].split("|") for i,j in enumerate(h)]
+    t=model_outputs["sentence"].replace("\n"," ")
+    u="# text = "+t+"\n"
+    for i,j in enumerate(d):
+      u+="\t".join([str(i+1),j,"_",q[i][0],"_","_" if len(q[i])<3 else "|".join(q[i][1:-1]),str(0 if h[i]==i else h[i]+1),"root" if q[i][-1]=="root" else q[i][-1][2:],"_","_" if i+1<len(d) and w[i]["end"]<w[i+1]["start"] else "SpaceAfter=No"])+"\n"
+    return u+"\n"
+  def chu_liu_edmonds(self,matrix):
+    h=numpy.nanargmax(matrix,axis=0)
+    x=[-1 if i==j else j for i,j in enumerate(h)]
+    for b in [lambda x,i,j:-1 if i not in x else x[i],lambda x,i,j:-1 if j<0 else x[j]]:
+      y=[]
+      while x!=y:
+        y=list(x)
+        for i,j in enumerate(x):
+          x[i]=b(x,i,j)
+      if max(x)<0:
+        return h
+    y,x=[i for i,j in enumerate(x) if j==max(x)],[i for i,j in enumerate(x) if j<max(x)]
+    z=matrix-numpy.nanmax(matrix,axis=0)
+    m=numpy.block([[z[x,:][:,x],numpy.nanmax(z[x,:][:,y],axis=1).reshape(len(x),1)],[numpy.nanmax(z[y,:][:,x],axis=0),numpy.nanmax(z[y,y])]])
+    k=[j if i==len(x) else x[j] if j<len(x) else y[numpy.nanargmax(z[y,x[i]])] for i,j in enumerate(self.chu_liu_edmonds(m))]
+    h=[j if i in y else k[x.index(i)] for i,j in enumerate(h)]
+    i=y[numpy.nanargmax(z[x[k[-1]],y] if k[-1]<len(x) else z[y,y])]
+    h[i]=x[k[-1]] if k[-1]<len(x) else i
+    return h