initial release

README.md

@@ -0,0 +1,30 @@
+---
+language:
+- "th"
+tags:
+- "thai"
+- "pos"
+- "dependency-parsing"
+base_model: scb10x/llama3.2-typhoon2-1b
+datasets:
+- "universal_dependencies"
+license: "llama3.2"
+pipeline_tag: "token-classification"
+widget:
+- text: "หลายหัวดีกว่าหัวเดียว"
+---
+
+# llama3.2-typhoon2-1b-ud-embeds
+
+## Model Description
+
+This is a LLaMA model pre-trained for POS-tagging and dependency-parsing, derived from [llama3.2-typhoon2-1b](https://huggingface.co/scb10x/llama3.2-typhoon2-1b) 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/llama3.2-typhoon2-1b-ud-embeds",trust_remote_code=True)
+print(nlp("หลายหัวดีกว่าหัวเดียว"))
+```
+

config.json

@@ -0,0 +1,1832 @@
+{
+  "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.UniversalDependenciesPipeline",
+      "pt": "AutoModelForTokenClassification"
+    }
+  },
+  "eos_token_id": 128009,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "ADP",
+    "1": "ADP.",
+    "2": "ADP|Foreign=Yes|_",
+    "3": "ADP|Foreign=Yes|l-case",
+    "4": "ADP|NounType=Class|_",
+    "5": "ADP|NounType=Class|l-case",
+    "6": "ADP|Prefix=Yes|_",
+    "7": "ADP|Prefix=Yes|l-case",
+    "8": "ADP|Prefix=Yes|l-mark",
+    "9": "ADP|_",
+    "10": "ADP|l-acl",
+    "11": "ADP|l-advcl",
+    "12": "ADP|l-advmod",
+    "13": "ADP|l-case",
+    "14": "ADP|l-cc",
+    "15": "ADP|l-dep",
+    "16": "ADP|l-fixed",
+    "17": "ADP|l-flat",
+    "18": "ADP|l-mark",
+    "19": "ADP|l-nmod",
+    "20": "ADP|l-nsubj",
+    "21": "ADP|l-obl",
+    "22": "ADP|l-orphan",
+    "23": "ADP|r-acl",
+    "24": "ADP|r-advmod",
+    "25": "ADP|r-case",
+    "26": "ADP|r-compound",
+    "27": "ADP|r-conj",
+    "28": "ADP|r-fixed",
+    "29": "ADP|r-flat",
+    "30": "ADP|r-obl",
+    "31": "ADP|r-orphan",
+    "32": "ADP|root",
+    "33": "ADV",
+    "34": "ADV.",
+    "35": "ADV|Foreign=Yes|_",
+    "36": "ADV|Foreign=Yes|l-advmod",
+    "37": "ADV|Foreign=Yes|r-advmod",
+    "38": "ADV|NumType=Mult|_",
+    "39": "ADV|NumType=Mult|r-advmod",
+    "40": "ADV|PartType=Adv|_",
+    "41": "ADV|PartType=Adv|l-advmod",
+    "42": "ADV|PartType=Adv|l-mark",
+    "43": "ADV|PartType=Adv|r-advmod",
+    "44": "ADV|PartType=Enp|_",
+    "45": "ADV|PartType=Enp|l-advmod",
+    "46": "ADV|PartType=Enp|r-advmod",
+    "47": "ADV|PartType=Int|_",
+    "48": "ADV|PartType=Int|r-advmod",
+    "49": "ADV|PartType=Int|r-fixed",
+    "50": "ADV|Prefix=Yes|_",
+    "51": "ADV|Prefix=Yes|l-advmod",
+    "52": "ADV|Prefix=Yes|l-mark",
+    "53": "ADV|Prefix=Yes|r-advmod",
+    "54": "ADV|_",
+    "55": "ADV|l-acl",
+    "56": "ADV|l-advcl",
+    "57": "ADV|l-advmod",
+    "58": "ADV|l-aux",
+    "59": "ADV|l-case",
+    "60": "ADV|l-compound",
+    "61": "ADV|l-dep",
+    "62": "ADV|l-det",
+    "63": "ADV|l-discourse",
+    "64": "ADV|l-fixed",
+    "65": "ADV|l-mark",
+    "66": "ADV|l-orphan",
+    "67": "ADV|r-acl",
+    "68": "ADV|r-advcl",
+    "69": "ADV|r-advmod",
+    "70": "ADV|r-aux",
+    "71": "ADV|r-compound",
+    "72": "ADV|r-conj",
+    "73": "ADV|r-det",
+    "74": "ADV|r-fixed",
+    "75": "ADV|r-flat",
+    "76": "ADV|r-mark",
+    "77": "ADV|r-nmod",
+    "78": "ADV|r-obj",
+    "79": "ADV|r-orphan",
+    "80": "ADV|r-xcomp",
+    "81": "ADV|root",
+    "82": "AUX",
+    "83": "AUX.",
+    "84": "AUX|Foreign=Yes|_",
+    "85": "AUX|Foreign=Yes|l-aux",
+    "86": "AUX|NounType=Class|_",
+    "87": "AUX|NounType=Class|r-appos",
+    "88": "AUX|Prefix=Yes|_",
+    "89": "AUX|Prefix=Yes|l-aux",
+    "90": "AUX|Prefix=Yes|r-aux",
+    "91": "AUX|VerbType=Cop|_",
+    "92": "AUX|VerbType=Cop|l-acl",
+    "93": "AUX|VerbType=Cop|l-advcl",
+    "94": "AUX|VerbType=Cop|l-aux",
+    "95": "AUX|VerbType=Cop|l-cop",
+    "96": "AUX|VerbType=Cop|r-acl",
+    "97": "AUX|VerbType=Cop|r-advcl",
+    "98": "AUX|VerbType=Cop|r-aux",
+    "99": "AUX|VerbType=Cop|r-conj",
+    "100": "AUX|VerbType=Cop|r-mark",
+    "101": "AUX|VerbType=Cop|root",
+    "102": "AUX|_",
+    "103": "AUX|l-advmod",
+    "104": "AUX|l-aux",
+    "105": "AUX|l-cop",
+    "106": "AUX|l-mark",
+    "107": "AUX|r-acl",
+    "108": "AUX|r-advmod",
+    "109": "AUX|r-aux",
+    "110": "AUX|r-ccomp",
+    "111": "AUX|r-clf",
+    "112": "AUX|r-compound",
+    "113": "AUX|r-conj",
+    "114": "AUX|r-fixed",
+    "115": "AUX|root",
+    "116": "B-ADP",
+    "117": "B-ADP.",
+    "118": "B-ADV",
+    "119": "B-ADV.",
+    "120": "B-AUX",
+    "121": "B-AUX.",
+    "122": "B-CCONJ",
+    "123": "B-CCONJ.",
+    "124": "B-DET",
+    "125": "B-DET.",
+    "126": "B-NOUN",
+    "127": "B-NOUN.",
+    "128": "B-NUM",
+    "129": "B-NUM.",
+    "130": "B-PART",
+    "131": "B-PART.",
+    "132": "B-PRON",
+    "133": "B-PRON.",
+    "134": "B-PROPN",
+    "135": "B-PROPN.",
+    "136": "B-PUNCT",
+    "137": "B-PUNCT.",
+    "138": "B-SCONJ",
+    "139": "B-SCONJ.",
+    "140": "B-SYM",
+    "141": "B-SYM.",
+    "142": "B-VERB",
+    "143": "B-VERB.",
+    "144": "CCONJ",
+    "145": "CCONJ.",
+    "146": "CCONJ|Foreign=Yes|_",
+    "147": "CCONJ|Foreign=Yes|l-cc",
+    "148": "CCONJ|PronType=Prs|_",
+    "149": "CCONJ|PronType=Prs|l-cc",
+    "150": "CCONJ|_",
+    "151": "CCONJ|l-advmod",
+    "152": "CCONJ|l-case",
+    "153": "CCONJ|l-cc",
+    "154": "CCONJ|l-conj",
+    "155": "CCONJ|l-discourse",
+    "156": "CCONJ|l-fixed",
+    "157": "CCONJ|l-flat",
+    "158": "CCONJ|l-mark",
+    "159": "CCONJ|l-nsubj",
+    "160": "CCONJ|l-obj",
+    "161": "CCONJ|l-orphan",
+    "162": "CCONJ|r-cc",
+    "163": "CCONJ|r-compound",
+    "164": "CCONJ|r-fixed",
+    "165": "CCONJ|r-mark",
+    "166": "DET",
+    "167": "DET.",
+    "168": "DET|NumType=Mult|_",
+    "169": "DET|NumType=Mult|l-det",
+    "170": "DET|PartType=Emp|_",
+    "171": "DET|PartType=Emp|r-det",
+    "172": "DET|PartType=Int|_",
+    "173": "DET|PartType=Int|r-det",
+    "174": "DET|_",
+    "175": "DET|l-compound",
+    "176": "DET|l-det",
+    "177": "DET|l-discourse",
+    "178": "DET|l-nsubj",
+    "179": "DET|l-obl",
+    "180": "DET|l-orphan",
+    "181": "DET|r-advmod",
+    "182": "DET|r-compound",
+    "183": "DET|r-conj",
+    "184": "DET|r-dep",
+    "185": "DET|r-det",
+    "186": "DET|r-fixed",
+    "187": "DET|r-flat",
+    "188": "DET|r-list",
+    "189": "DET|r-nmod",
+    "190": "DET|r-nummod",
+    "191": "DET|r-obl",
+    "192": "DET|r-orphan",
+    "193": "I-ADP",
+    "194": "I-ADP.",
+    "195": "I-ADV",
+    "196": "I-ADV.",
+    "197": "I-AUX",
+    "198": "I-AUX.",
+    "199": "I-CCONJ",
+    "200": "I-CCONJ.",
+    "201": "I-DET",
+    "202": "I-DET.",
+    "203": "I-NOUN",
+    "204": "I-NOUN.",
+    "205": "I-NUM",
+    "206": "I-NUM.",
+    "207": "I-PART",
+    "208": "I-PART.",
+    "209": "I-PRON",
+    "210": "I-PRON.",
+    "211": "I-PROPN",
+    "212": "I-PROPN.",
+    "213": "I-PUNCT",
+    "214": "I-PUNCT.",
+    "215": "I-SCONJ",
+    "216": "I-SCONJ.",
+    "217": "I-SYM",
+    "218": "I-SYM.",
+    "219": "I-VERB",
+    "220": "I-VERB.",
+    "221": "NOUN",
+    "222": "NOUN.",
+    "223": "NOUN|Abbr=Yes|Foreign=Yes|_",
+    "224": "NOUN|Abbr=Yes|Foreign=Yes|r-nmod",
+    "225": "NOUN|Abbr=Yes|Prefix=Yes|_",
+    "226": "NOUN|Abbr=Yes|Prefix=Yes|l-flat",
+    "227": "NOUN|Abbr=Yes|_",
+    "228": "NOUN|Abbr=Yes|l-flat",
+    "229": "NOUN|Abbr=Yes|l-nmod",
+    "230": "NOUN|Abbr=Yes|l-nsubj",
+    "231": "NOUN|Abbr=Yes|l-obl",
+    "232": "NOUN|Abbr=Yes|r-acl",
+    "233": "NOUN|Abbr=Yes|r-appos",
+    "234": "NOUN|Abbr=Yes|r-clf",
+    "235": "NOUN|Abbr=Yes|r-conj",
+    "236": "NOUN|Abbr=Yes|r-fixed",
+    "237": "NOUN|Abbr=Yes|r-flat",
+    "238": "NOUN|Abbr=Yes|r-nmod",
+    "239": "NOUN|Abbr=Yes|r-obj",
+    "240": "NOUN|Abbr=Yes|r-obl",
+    "241": "NOUN|Foreign=Yes|NounType=Class|_",
+    "242": "NOUN|Foreign=Yes|NounType=Class|r-clf",
+    "243": "NOUN|Foreign=Yes|NounType=Class|r-obj",
+    "244": "NOUN|Foreign=Yes|Prefix=Yes|_",
+    "245": "NOUN|Foreign=Yes|Prefix=Yes|l-flat",
+    "246": "NOUN|Foreign=Yes|Prefix=Yes|r-appos",
+    "247": "NOUN|Foreign=Yes|_",
+    "248": "NOUN|Foreign=Yes|l-dislocated",
+    "249": "NOUN|Foreign=Yes|l-flat",
+    "250": "NOUN|Foreign=Yes|l-nmod",
+    "251": "NOUN|Foreign=Yes|l-nsubj",
+    "252": "NOUN|Foreign=Yes|l-obl",
+    "253": "NOUN|Foreign=Yes|r-acl",
+    "254": "NOUN|Foreign=Yes|r-advcl",
+    "255": "NOUN|Foreign=Yes|r-advmod",
+    "256": "NOUN|Foreign=Yes|r-appos",
+    "257": "NOUN|Foreign=Yes|r-ccomp",
+    "258": "NOUN|Foreign=Yes|r-clf",
+    "259": "NOUN|Foreign=Yes|r-compound",
+    "260": "NOUN|Foreign=Yes|r-conj",
+    "261": "NOUN|Foreign=Yes|r-flat",
+    "262": "NOUN|Foreign=Yes|r-iobj",
+    "263": "NOUN|Foreign=Yes|r-list",
+    "264": "NOUN|Foreign=Yes|r-nmod",
+    "265": "NOUN|Foreign=Yes|r-obj",
+    "266": "NOUN|Foreign=Yes|r-obl",
+    "267": "NOUN|Foreign=Yes|r-xcomp",
+    "268": "NOUN|Foreign=Yes|root",
+    "269": "NOUN|NameType=Com|_",
+    "270": "NOUN|NameType=Com|r-nmod",
+    "271": "NOUN|NameType=Geo|_",
+    "272": "NOUN|NameType=Geo|l-nsubj",
+    "273": "NOUN|NameType=Geo|r-nmod",
+    "274": "NOUN|NameType=Geo|r-obj",
+    "275": "NOUN|NameType=Nat|_",
+    "276": "NOUN|NameType=Nat|r-nmod",
+    "277": "NOUN|NameType=Oth|_",
+    "278": "NOUN|NameType=Oth|l-nsubj",
+    "279": "NOUN|NameType=Oth|r-conj",
+    "280": "NOUN|NameType=Oth|r-flat",
+    "281": "NOUN|NameType=Oth|r-nmod",
+    "282": "NOUN|NameType=Pro|_",
+    "283": "NOUN|NameType=Pro|r-nmod",
+    "284": "NOUN|NameType=Prs|_",
+    "285": "NOUN|NameType=Prs|l-nsubj",
+    "286": "NOUN|NameType=Prs|r-nmod",
+    "287": "NOUN|NounType=Class|Prefix=Yes|_",
+    "288": "NOUN|NounType=Class|Prefix=Yes|l-advcl",
+    "289": "NOUN|NounType=Class|Prefix=Yes|l-advmod",
+    "290": "NOUN|NounType=Class|Prefix=Yes|l-mark",
+    "291": "NOUN|NounType=Class|Prefix=Yes|l-nmod",
+    "292": "NOUN|NounType=Class|Prefix=Yes|l-nsubj",
+    "293": "NOUN|NounType=Class|Prefix=Yes|r-advcl",
+    "294": "NOUN|NounType=Class|Prefix=Yes|r-clf",
+    "295": "NOUN|NounType=Class|Prefix=Yes|r-nmod",
+    "296": "NOUN|NounType=Class|Prefix=Yes|r-obj",
+    "297": "NOUN|NounType=Class|_",
+    "298": "NOUN|NounType=Class|l-advcl",
+    "299": "NOUN|NounType=Class|l-advmod",
+    "300": "NOUN|NounType=Class|l-clf",
+    "301": "NOUN|NounType=Class|l-dislocated",
+    "302": "NOUN|NounType=Class|l-nmod",
+    "303": "NOUN|NounType=Class|l-nsubj",
+    "304": "NOUN|NounType=Class|l-obj",
+    "305": "NOUN|NounType=Class|l-obl",
+    "306": "NOUN|NounType=Class|r-acl",
+    "307": "NOUN|NounType=Class|r-advcl",
+    "308": "NOUN|NounType=Class|r-advmod",
+    "309": "NOUN|NounType=Class|r-appos",
+    "310": "NOUN|NounType=Class|r-cc",
+    "311": "NOUN|NounType=Class|r-ccomp",
+    "312": "NOUN|NounType=Class|r-clf",
+    "313": "NOUN|NounType=Class|r-compound",
+    "314": "NOUN|NounType=Class|r-conj",
+    "315": "NOUN|NounType=Class|r-dislocated",
+    "316": "NOUN|NounType=Class|r-fixed",
+    "317": "NOUN|NounType=Class|r-flat",
+    "318": "NOUN|NounType=Class|r-iobj",
+    "319": "NOUN|NounType=Class|r-list",
+    "320": "NOUN|NounType=Class|r-nmod",
+    "321": "NOUN|NounType=Class|r-nummod",
+    "322": "NOUN|NounType=Class|r-obj",
+    "323": "NOUN|NounType=Class|r-obl",
+    "324": "NOUN|NounType=Class|r-orphan",
+    "325": "NOUN|NounType=Class|r-xcomp",
+    "326": "NOUN|NounType=Class|root",
+    "327": "NOUN|NumType=Mult|_",
+    "328": "NOUN|NumType=Mult|r-advcl",
+    "329": "NOUN|NumType=Mult|r-nmod",
+    "330": "NOUN|NumType=Mult|r-obj",
+    "331": "NOUN|PartType=Enp|_",
+    "332": "NOUN|PartType=Enp|r-obj",
+    "333": "NOUN|PartType=Enp|r-obl",
+    "334": "NOUN|PartType=Int|_",
+    "335": "NOUN|PartType=Int|r-obj",
+    "336": "NOUN|PartType=Res|_",
+    "337": "NOUN|PartType=Res|r-nmod",
+    "338": "NOUN|PartType=Res|r-obj",
+    "339": "NOUN|Prefix=Yes|_",
+    "340": "NOUN|Prefix=Yes|l-acl",
+    "341": "NOUN|Prefix=Yes|l-advcl",
+    "342": "NOUN|Prefix=Yes|l-clf",
+    "343": "NOUN|Prefix=Yes|l-csubj",
+    "344": "NOUN|Prefix=Yes|l-dislocated",
+    "345": "NOUN|Prefix=Yes|l-flat",
+    "346": "NOUN|Prefix=Yes|l-nmod",
+    "347": "NOUN|Prefix=Yes|l-nsubj",
+    "348": "NOUN|Prefix=Yes|l-obj",
+    "349": "NOUN|Prefix=Yes|l-obl",
+    "350": "NOUN|Prefix=Yes|r-acl",
+    "351": "NOUN|Prefix=Yes|r-advcl",
+    "352": "NOUN|Prefix=Yes|r-advmod",
+    "353": "NOUN|Prefix=Yes|r-appos",
+    "354": "NOUN|Prefix=Yes|r-case",
+    "355": "NOUN|Prefix=Yes|r-cc",
+    "356": "NOUN|Prefix=Yes|r-ccomp",
+    "357": "NOUN|Prefix=Yes|r-clf",
+    "358": "NOUN|Prefix=Yes|r-compound",
+    "359": "NOUN|Prefix=Yes|r-conj",
+    "360": "NOUN|Prefix=Yes|r-dislocated",
+    "361": "NOUN|Prefix=Yes|r-fixed",
+    "362": "NOUN|Prefix=Yes|r-flat",
+    "363": "NOUN|Prefix=Yes|r-iobj",
+    "364": "NOUN|Prefix=Yes|r-list",
+    "365": "NOUN|Prefix=Yes|r-nmod",
+    "366": "NOUN|Prefix=Yes|r-nummod",
+    "367": "NOUN|Prefix=Yes|r-obj",
+    "368": "NOUN|Prefix=Yes|r-obl",
+    "369": "NOUN|Prefix=Yes|r-orphan",
+    "370": "NOUN|Prefix=Yes|r-xcomp",
+    "371": "NOUN|Prefix=Yes|root",
+    "372": "NOUN|_",
+    "373": "NOUN|l-acl",
+    "374": "NOUN|l-advcl",
+    "375": "NOUN|l-advmod",
+    "376": "NOUN|l-case",
+    "377": "NOUN|l-ccomp",
+    "378": "NOUN|l-compound",
+    "379": "NOUN|l-csubj",
+    "380": "NOUN|l-discourse",
+    "381": "NOUN|l-dislocated",
+    "382": "NOUN|l-expl",
+    "383": "NOUN|l-flat",
+    "384": "NOUN|l-iobj",
+    "385": "NOUN|l-mark",
+    "386": "NOUN|l-nmod",
+    "387": "NOUN|l-nsubj",
+    "388": "NOUN|l-nummod",
+    "389": "NOUN|l-obj",
+    "390": "NOUN|l-obl",
+    "391": "NOUN|l-orphan",
+    "392": "NOUN|l-vocative",
+    "393": "NOUN|r-acl",
+    "394": "NOUN|r-advcl",
+    "395": "NOUN|r-advmod",
+    "396": "NOUN|r-appos",
+    "397": "NOUN|r-case",
+    "398": "NOUN|r-cc",
+    "399": "NOUN|r-ccomp",
+    "400": "NOUN|r-clf",
+    "401": "NOUN|r-compound",
+    "402": "NOUN|r-conj",
+    "403": "NOUN|r-cop",
+    "404": "NOUN|r-discourse",
+    "405": "NOUN|r-dislocated",
+    "406": "NOUN|r-fixed",
+    "407": "NOUN|r-flat",
+    "408": "NOUN|r-iobj",
+    "409": "NOUN|r-list",
+    "410": "NOUN|r-mark",
+    "411": "NOUN|r-nmod",
+    "412": "NOUN|r-nsubj",
+    "413": "NOUN|r-nummod",
+    "414": "NOUN|r-obj",
+    "415": "NOUN|r-obl",
+    "416": "NOUN|r-orphan",
+    "417": "NOUN|r-parataxis",
+    "418": "NOUN|r-xcomp",
+    "419": "NOUN|root",
+    "420": "NUM",
+    "421": "NUM.",
+    "422": "NUM|Abbr=Yes|_",
+    "423": "NUM|Abbr=Yes|r-flat",
+    "424": "NUM|Abbr=Yes|r-nummod",
+    "425": "NUM|Abbr=Yes|r-obj",
+    "426": "NUM|Foreign=Yes|_",
+    "427": "NUM|Foreign=Yes|r-clf",
+    "428": "NUM|NumType=Mult|_",
+    "429": "NUM|NumType=Mult|l-advmod",
+    "430": "NUM|NumType=Mult|l-nummod",
+    "431": "NUM|NumType=Mult|r-advmod",
+    "432": "NUM|Prefix=Yes|_",
+    "433": "NUM|Prefix=Yes|l-nummod",
+    "434": "NUM|_",
+    "435": "NUM|l-advcl",
+    "436": "NUM|l-advmod",
+    "437": "NUM|l-case",
+    "438": "NUM|l-clf",
+    "439": "NUM|l-dep",
+    "440": "NUM|l-flat",
+    "441": "NUM|l-nmod",
+    "442": "NUM|l-nsubj",
+    "443": "NUM|l-nummod",
+    "444": "NUM|l-obl",
+    "445": "NUM|r-acl",
+    "446": "NUM|r-advmod",
+    "447": "NUM|r-appos",
+    "448": "NUM|r-ccomp",
+    "449": "NUM|r-compound",
+    "450": "NUM|r-conj",
+    "451": "NUM|r-det",
+    "452": "NUM|r-fixed",
+    "453": "NUM|r-flat",
+    "454": "NUM|r-iobj",
+    "455": "NUM|r-nmod",
+    "456": "NUM|r-nummod",
+    "457": "NUM|r-obj",
+    "458": "NUM|r-obl",
+    "459": "NUM|root",
+    "460": "PART",
+    "461": "PART.",
+    "462": "PART|NameType=Oth|_",
+    "463": "PART|NameType=Oth|l-advmod",
+    "464": "PART|NounType=Class|PartType=Emp|Prefix=Yes|_",
+    "465": "PART|NounType=Class|PartType=Emp|Prefix=Yes|l-mark",
+    "466": "PART|NounType=Class|PartType=Emp|_",
+    "467": "PART|NounType=Class|PartType=Emp|l-mark",
+    "468": "PART|NounType=Class|Prefix=Yes|_",
+    "469": "PART|NounType=Class|Prefix=Yes|l-mark",
+    "470": "PART|NumType=Mult|PartType=Emp|_",
+    "471": "PART|NumType=Mult|PartType=Emp|l-mark",
+    "472": "PART|PartType=Adj|_",
+    "473": "PART|PartType=Adj|l-mark",
+    "474": "PART|PartType=Adj|l-orphan",
+    "475": "PART|PartType=Adj|r-acl",
+    "476": "PART|PartType=Adj|r-compound",
+    "477": "PART|PartType=Adj|r-nmod",
+    "478": "PART|PartType=Adv|_",
+    "479": "PART|PartType=Adv|l-advmod",
+    "480": "PART|PartType=Adv|l-mark",
+    "481": "PART|PartType=Adv|r-advmod",
+    "482": "PART|PartType=Emp|Prefix=Yes|_",
+    "483": "PART|PartType=Emp|Prefix=Yes|l-advmod",
+    "484": "PART|PartType=Emp|Prefix=Yes|l-aux",
+    "485": "PART|PartType=Emp|Prefix=Yes|l-mark",
+    "486": "PART|PartType=Emp|_",
+    "487": "PART|PartType=Emp|l-advmod",
+    "488": "PART|PartType=Emp|l-case",
+    "489": "PART|PartType=Emp|l-discourse",
+    "490": "PART|PartType=Emp|l-mark",
+    "491": "PART|PartType=Emp|r-acl",
+    "492": "PART|PartType=Emp|r-advmod",
+    "493": "PART|PartType=Emp|r-aux",
+    "494": "PART|PartType=Emp|r-compound",
+    "495": "PART|PartType=Emp|r-det",
+    "496": "PART|PartType=Emp|r-fixed",
+    "497": "PART|PartType=Emp|r-mark",
+    "498": "PART|PartType=Emp|r-nmod",
+    "499": "PART|PartType=Enp|_",
+    "500": "PART|PartType=Enp|l-discourse",
+    "501": "PART|PartType=Enp|r-acl",
+    "502": "PART|PartType=Enp|r-advmod",
+    "503": "PART|PartType=Enp|r-compound",
+    "504": "PART|PartType=Enp|r-dep",
+    "505": "PART|PartType=Enp|r-det",
+    "506": "PART|PartType=Enp|r-discourse",
+    "507": "PART|PartType=Enp|r-fixed",
+    "508": "PART|PartType=Enp|r-obl",
+    "509": "PART|PartType=Int|_",
+    "510": "PART|PartType=Int|l-advmod",
+    "511": "PART|PartType=Int|l-mark",
+    "512": "PART|PartType=Int|r-acl",
+    "513": "PART|PartType=Int|r-advmod",
+    "514": "PART|PartType=Int|r-dep",
+    "515": "PART|PartType=Int|r-discourse",
+    "516": "PART|PartType=Int|r-nmod",
+    "517": "PART|PartType=Int|r-obj",
+    "518": "PART|PartType=Int|r-obl",
+    "519": "PART|PartType=Neg|_",
+    "520": "PART|PartType=Neg|l-advcl",
+    "521": "PART|PartType=Neg|l-advmod",
+    "522": "PART|PartType=Neg|l-aux",
+    "523": "PART|PartType=Neg|l-mark",
+    "524": "PART|PartType=Neg|r-acl",
+    "525": "PART|PartType=Neg|r-advmod",
+    "526": "PART|PartType=Neg|r-fixed",
+    "527": "PART|PartType=Res|_",
+    "528": "PART|PartType=Res|r-advmod",
+    "529": "PART|PartType=Res|r-discourse",
+    "530": "PART|PartType=Res|r-fixed",
+    "531": "PART|Prefix=Yes|_",
+    "532": "PART|Prefix=Yes|l-advmod",
+    "533": "PART|Prefix=Yes|l-aux",
+    "534": "PART|Prefix=Yes|l-mark",
+    "535": "PART|Prefix=Yes|r-acl",
+    "536": "PART|Prefix=Yes|r-nmod",
+    "537": "PART|_",
+    "538": "PART|l-advmod",
+    "539": "PART|l-discourse",
+    "540": "PART|l-mark",
+    "541": "PART|l-nsubj",
+    "542": "PART|r-acl",
+    "543": "PART|r-advmod",
+    "544": "PART|r-discourse",
+    "545": "PART|r-fixed",
+    "546": "PART|r-mark",
+    "547": "PART|r-obj",
+    "548": "PRON",
+    "549": "PRON.",
+    "550": "PRON|NounType=Class|_",
+    "551": "PRON|NounType=Class|r-clf",
+    "552": "PRON|PronType=Prs|_",
+    "553": "PRON|PronType=Prs|l-advmod",
+    "554": "PRON|PronType=Prs|l-expl",
+    "555": "PRON|PronType=Prs|l-nsubj",
+    "556": "PRON|PronType=Prs|l-obj",
+    "557": "PRON|PronType=Prs|l-obl",
+    "558": "PRON|PronType=Prs|r-advcl",
+    "559": "PRON|PronType=Prs|r-advmod",
+    "560": "PRON|PronType=Prs|r-ccomp",
+    "561": "PRON|PronType=Prs|r-clf",
+    "562": "PRON|PronType=Prs|r-conj",
+    "563": "PRON|PronType=Prs|r-nmod",
+    "564": "PRON|PronType=Prs|r-nsubj",
+    "565": "PRON|PronType=Prs|r-obj",
+    "566": "PRON|PronType=Prs|r-obl",
+    "567": "PRON|PronType=Prs|root",
+    "568": "PRON|PronType=Rcp|_",
+    "569": "PRON|PronType=Rcp|r-advmod",
+    "570": "PRON|PronType=Rcp|r-iobj",
+    "571": "PRON|PronType=Rcp|r-nmod",
+    "572": "PRON|PronType=Rcp|r-obj",
+    "573": "PRON|PronType=Rcp|r-obl",
+    "574": "PRON|_",
+    "575": "PRON|l-advcl",
+    "576": "PRON|l-advmod",
+    "577": "PRON|l-compound",
+    "578": "PRON|l-csubj",
+    "579": "PRON|l-dislocated",
+    "580": "PRON|l-expl",
+    "581": "PRON|l-iobj",
+    "582": "PRON|l-mark",
+    "583": "PRON|l-nsubj",
+    "584": "PRON|l-obj",
+    "585": "PRON|l-obl",
+    "586": "PRON|r-acl",
+    "587": "PRON|r-advmod",
+    "588": "PRON|r-appos",
+    "589": "PRON|r-ccomp",
+    "590": "PRON|r-compound",
+    "591": "PRON|r-conj",
+    "592": "PRON|r-det",
+    "593": "PRON|r-discourse",
+    "594": "PRON|r-fixed",
+    "595": "PRON|r-flat",
+    "596": "PRON|r-iobj",
+    "597": "PRON|r-nmod",
+    "598": "PRON|r-nsubj",
+    "599": "PRON|r-obj",
+    "600": "PRON|r-obl",
+    "601": "PROPN",
+    "602": "PROPN.",
+    "603": "PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth|_",
+    "604": "PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth|r-obj",
+    "605": "PROPN|Abbr=Yes|NameType=Com|_",
+    "606": "PROPN|Abbr=Yes|NameType=Com|r-advmod",
+    "607": "PROPN|Abbr=Yes|NameType=Com|r-nmod",
+    "608": "PROPN|Abbr=Yes|_",
+    "609": "PROPN|Abbr=Yes|l-nmod",
+    "610": "PROPN|Abbr=Yes|l-nsubj",
+    "611": "PROPN|Abbr=Yes|r-nmod",
+    "612": "PROPN|Foreign=Yes|NameType=Com|_",
+    "613": "PROPN|Foreign=Yes|NameType=Com|l-nsubj",
+    "614": "PROPN|Foreign=Yes|NameType=Com|r-list",
+    "615": "PROPN|Foreign=Yes|NameType=Com|r-nmod",
+    "616": "PROPN|Foreign=Yes|NameType=Com|r-obl",
+    "617": "PROPN|Foreign=Yes|NameType=Geo|_",
+    "618": "PROPN|Foreign=Yes|NameType=Geo|r-obj",
+    "619": "PROPN|Foreign=Yes|NameType=Geo|r-obl",
+    "620": "PROPN|Foreign=Yes|NameType=Giv|_",
+    "621": "PROPN|Foreign=Yes|NameType=Giv|l-nsubj",
+    "622": "PROPN|Foreign=Yes|NameType=Oth|_",
+    "623": "PROPN|Foreign=Yes|NameType=Oth|r-conj",
+    "624": "PROPN|Foreign=Yes|NameType=Oth|r-flat",
+    "625": "PROPN|Foreign=Yes|NameType=Oth|r-nmod",
+    "626": "PROPN|Foreign=Yes|NameType=Prs|_",
+    "627": "PROPN|Foreign=Yes|NameType=Prs|l-flat",
+    "628": "PROPN|Foreign=Yes|NameType=Prs|l-nsubj",
+    "629": "PROPN|Foreign=Yes|NameType=Prs|r-conj",
+    "630": "PROPN|Foreign=Yes|NameType=Prs|r-flat",
+    "631": "PROPN|Foreign=Yes|NameType=Prs|r-nmod",
+    "632": "PROPN|Foreign=Yes|NameType=Prs|r-obj",
+    "633": "PROPN|Foreign=Yes|NameType=Prs|r-obl",
+    "634": "PROPN|Foreign=Yes|NameType=Sur|_",
+    "635": "PROPN|Foreign=Yes|NameType=Sur|r-flat",
+    "636": "PROPN|Foreign=Yes|_",
+    "637": "PROPN|Foreign=Yes|l-flat",
+    "638": "PROPN|Foreign=Yes|l-nmod",
+    "639": "PROPN|Foreign=Yes|l-nsubj",
+    "640": "PROPN|Foreign=Yes|l-obl",
+    "641": "PROPN|Foreign=Yes|r-appos",
+    "642": "PROPN|Foreign=Yes|r-ccomp",
+    "643": "PROPN|Foreign=Yes|r-compound",
+    "644": "PROPN|Foreign=Yes|r-conj",
+    "645": "PROPN|Foreign=Yes|r-flat",
+    "646": "PROPN|Foreign=Yes|r-iobj",
+    "647": "PROPN|Foreign=Yes|r-list",
+    "648": "PROPN|Foreign=Yes|r-nmod",
+    "649": "PROPN|Foreign=Yes|r-nsubj",
+    "650": "PROPN|Foreign=Yes|r-obj",
+    "651": "PROPN|Foreign=Yes|r-obl",
+    "652": "PROPN|Foreign=Yes|root",
+    "653": "PROPN|NameType=Com|_",
+    "654": "PROPN|NameType=Com|l-nsubj",
+    "655": "PROPN|NameType=Com|l-obl",
+    "656": "PROPN|NameType=Com|r-appos",
+    "657": "PROPN|NameType=Com|r-conj",
+    "658": "PROPN|NameType=Com|r-flat",
+    "659": "PROPN|NameType=Com|r-list",
+    "660": "PROPN|NameType=Com|r-nmod",
+    "661": "PROPN|NameType=Com|r-nsubj",
+    "662": "PROPN|NameType=Com|r-obj",
+    "663": "PROPN|NameType=Com|r-obl",
+    "664": "PROPN|NameType=Geo|_",
+    "665": "PROPN|NameType=Geo|l-nsubj",
+    "666": "PROPN|NameType=Geo|l-obl",
+    "667": "PROPN|NameType=Geo|r-compound",
+    "668": "PROPN|NameType=Geo|r-conj",
+    "669": "PROPN|NameType=Geo|r-flat",
+    "670": "PROPN|NameType=Geo|r-list",
+    "671": "PROPN|NameType=Geo|r-nmod",
+    "672": "PROPN|NameType=Geo|r-nsubj",
+    "673": "PROPN|NameType=Geo|r-nummod",
+    "674": "PROPN|NameType=Geo|r-obj",
+    "675": "PROPN|NameType=Geo|r-obl",
+    "676": "PROPN|NameType=Geo|root",
+    "677": "PROPN|NameType=Giv|_",
+    "678": "PROPN|NameType=Giv|l-dislocated",
+    "679": "PROPN|NameType=Giv|l-nsubj",
+    "680": "PROPN|NameType=Giv|l-obl",
+    "681": "PROPN|NameType=Giv|r-acl",
+    "682": "PROPN|NameType=Giv|r-appos",
+    "683": "PROPN|NameType=Giv|r-ccomp",
+    "684": "PROPN|NameType=Giv|r-conj",
+    "685": "PROPN|NameType=Giv|r-flat",
+    "686": "PROPN|NameType=Giv|r-list",
+    "687": "PROPN|NameType=Giv|r-nmod",
+    "688": "PROPN|NameType=Giv|r-nsubj",
+    "689": "PROPN|NameType=Giv|r-obj",
+    "690": "PROPN|NameType=Giv|r-obl",
+    "691": "PROPN|NameType=Giv|root",
+    "692": "PROPN|NameType=Nat|_",
+    "693": "PROPN|NameType=Nat|l-csubj",
+    "694": "PROPN|NameType=Nat|l-nsubj",
+    "695": "PROPN|NameType=Nat|l-obl",
+    "696": "PROPN|NameType=Nat|r-acl",
+    "697": "PROPN|NameType=Nat|r-appos",
+    "698": "PROPN|NameType=Nat|r-compound",
+    "699": "PROPN|NameType=Nat|r-conj",
+    "700": "PROPN|NameType=Nat|r-flat",
+    "701": "PROPN|NameType=Nat|r-list",
+    "702": "PROPN|NameType=Nat|r-nmod",
+    "703": "PROPN|NameType=Nat|r-nummod",
+    "704": "PROPN|NameType=Nat|r-obj",
+    "705": "PROPN|NameType=Nat|r-obl",
+    "706": "PROPN|NameType=Oth|_",
+    "707": "PROPN|NameType=Oth|l-dislocated",
+    "708": "PROPN|NameType=Oth|l-nsubj",
+    "709": "PROPN|NameType=Oth|r-acl",
+    "710": "PROPN|NameType=Oth|r-appos",
+    "711": "PROPN|NameType=Oth|r-compound",
+    "712": "PROPN|NameType=Oth|r-conj",
+    "713": "PROPN|NameType=Oth|r-flat",
+    "714": "PROPN|NameType=Oth|r-nmod",
+    "715": "PROPN|NameType=Oth|r-obj",
+    "716": "PROPN|NameType=Oth|r-obl",
+    "717": "PROPN|NameType=Oth|root",
+    "718": "PROPN|NameType=Pro|_",
+    "719": "PROPN|NameType=Pro|l-nsubj",
+    "720": "PROPN|NameType=Pro|l-obl",
+    "721": "PROPN|NameType=Pro|r-advcl",
+    "722": "PROPN|NameType=Pro|r-flat",
+    "723": "PROPN|NameType=Pro|r-nmod",
+    "724": "PROPN|NameType=Pro|r-obj",
+    "725": "PROPN|NameType=Prs|_",
+    "726": "PROPN|NameType=Prs|l-dislocated",
+    "727": "PROPN|NameType=Prs|l-nsubj",
+    "728": "PROPN|NameType=Prs|l-obl",
+    "729": "PROPN|NameType=Prs|l-vocative",
+    "730": "PROPN|NameType=Prs|r-conj",
+    "731": "PROPN|NameType=Prs|r-discourse",
+    "732": "PROPN|NameType=Prs|r-flat",
+    "733": "PROPN|NameType=Prs|r-list",
+    "734": "PROPN|NameType=Prs|r-nmod",
+    "735": "PROPN|NameType=Prs|r-obj",
+    "736": "PROPN|NameType=Prs|r-obl",
+    "737": "PROPN|NameType=Prs|r-vocative",
+    "738": "PROPN|NameType=Sur|_",
+    "739": "PROPN|NameType=Sur|l-nsubj",
+    "740": "PROPN|NameType=Sur|r-flat",
+    "741": "PROPN|NameType=Sur|r-nmod",
+    "742": "PROPN|NounType=Class|_",
+    "743": "PROPN|NounType=Class|r-clf",
+    "744": "PROPN|Prefix=Yes|_",
+    "745": "PROPN|Prefix=Yes|l-nsubj",
+    "746": "PROPN|Prefix=Yes|r-nmod",
+    "747": "PROPN|_",
+    "748": "PROPN|l-advmod",
+    "749": "PROPN|l-nsubj",
+    "750": "PROPN|l-obl",
+    "751": "PROPN|r-acl",
+    "752": "PROPN|r-advmod",
+    "753": "PROPN|r-appos",
+    "754": "PROPN|r-clf",
+    "755": "PROPN|r-compound",
+    "756": "PROPN|r-conj",
+    "757": "PROPN|r-fixed",
+    "758": "PROPN|r-flat",
+    "759": "PROPN|r-iobj",
+    "760": "PROPN|r-list",
+    "761": "PROPN|r-nmod",
+    "762": "PROPN|r-obj",
+    "763": "PROPN|r-obl",
+    "764": "PROPN|root",
+    "765": "PUNCT",
+    "766": "PUNCT.",
+    "767": "PUNCT|NounType=Class|_",
+    "768": "PUNCT|NounType=Class|r-punct",
+    "769": "PUNCT|_",
+    "770": "PUNCT|l-advmod",
+    "771": "PUNCT|l-dep",
+    "772": "PUNCT|l-punct",
+    "773": "PUNCT|r-dep",
+    "774": "PUNCT|r-punct",
+    "775": "SCONJ",
+    "776": "SCONJ.",
+    "777": "SCONJ|NumType=Mult|_",
+    "778": "SCONJ|NumType=Mult|l-mark",
+    "779": "SCONJ|Prefix=Yes|_",
+    "780": "SCONJ|Prefix=Yes|l-cc",
+    "781": "SCONJ|Prefix=Yes|l-mark",
+    "782": "SCONJ|VerbType=Cop|_",
+    "783": "SCONJ|VerbType=Cop|l-mark",
+    "784": "SCONJ|_",
+    "785": "SCONJ|l-advmod",
+    "786": "SCONJ|l-case",
+    "787": "SCONJ|l-cc",
+    "788": "SCONJ|l-discourse",
+    "789": "SCONJ|l-mark",
+    "790": "SCONJ|l-nsubj",
+    "791": "SCONJ|l-orphan",
+    "792": "SCONJ|r-advcl",
+    "793": "SCONJ|r-compound",
+    "794": "SCONJ|r-fixed",
+    "795": "SCONJ|r-flat",
+    "796": "SCONJ|r-mark",
+    "797": "SCONJ|r-orphan",
+    "798": "SCONJ|root",
+    "799": "SYM",
+    "800": "SYM.",
+    "801": "SYM|_",
+    "802": "SYM|l-dep",
+    "803": "SYM|r-clf",
+    "804": "SYM|r-nmod",
+    "805": "SYM|r-obj",
+    "806": "SYM|r-obl",
+    "807": "SYM|r-xcomp",
+    "808": "VERB",
+    "809": "VERB.",
+    "810": "VERB|Abbr=Yes|_",
+    "811": "VERB|Abbr=Yes|r-acl",
+    "812": "VERB|Foreign=Yes|_",
+    "813": "VERB|Foreign=Yes|l-nsubj",
+    "814": "VERB|Foreign=Yes|r-acl",
+    "815": "VERB|Foreign=Yes|r-advcl",
+    "816": "VERB|Foreign=Yes|r-ccomp",
+    "817": "VERB|Foreign=Yes|r-compound",
+    "818": "VERB|Foreign=Yes|r-conj",
+    "819": "VERB|Foreign=Yes|r-flat",
+    "820": "VERB|Foreign=Yes|r-nmod",
+    "821": "VERB|Foreign=Yes|r-xcomp",
+    "822": "VERB|Foreign=Yes|root",
+    "823": "VERB|NounType=Class|_",
+    "824": "VERB|NounType=Class|r-acl",
+    "825": "VERB|NounType=Class|r-compound",
+    "826": "VERB|PartType=Adj|_",
+    "827": "VERB|PartType=Adj|r-acl",
+    "828": "VERB|Prefix=Yes|_",
+    "829": "VERB|Prefix=Yes|l-acl",
+    "830": "VERB|Prefix=Yes|l-nsubj",
+    "831": "VERB|Prefix=Yes|r-acl",
+    "832": "VERB|Prefix=Yes|r-advcl",
+    "833": "VERB|Prefix=Yes|r-ccomp",
+    "834": "VERB|Prefix=Yes|r-compound",
+    "835": "VERB|Prefix=Yes|r-conj",
+    "836": "VERB|Prefix=Yes|r-parataxis",
+    "837": "VERB|Prefix=Yes|root",
+    "838": "VERB|VerbType=Cop|_",
+    "839": "VERB|VerbType=Cop|l-advmod",
+    "840": "VERB|VerbType=Cop|l-cop",
+    "841": "VERB|VerbType=Cop|r-acl",
+    "842": "VERB|VerbType=Cop|r-advcl",
+    "843": "VERB|VerbType=Cop|r-ccomp",
+    "844": "VERB|VerbType=Cop|r-compound",
+    "845": "VERB|VerbType=Cop|r-parataxis",
+    "846": "VERB|VerbType=Cop|root",
+    "847": "VERB|_",
+    "848": "VERB|l-acl",
+    "849": "VERB|l-advcl",
+    "850": "VERB|l-advmod",
+    "851": "VERB|l-case",
+    "852": "VERB|l-cc",
+    "853": "VERB|l-ccomp",
+    "854": "VERB|l-compound",
+    "855": "VERB|l-conj",
+    "856": "VERB|l-cop",
+    "857": "VERB|l-csubj",
+    "858": "VERB|l-discourse",
+    "859": "VERB|l-dislocated",
+    "860": "VERB|l-mark",
+    "861": "VERB|l-nsubj",
+    "862": "VERB|l-obl",
+    "863": "VERB|l-orphan",
+    "864": "VERB|l-xcomp",
+    "865": "VERB|r-acl",
+    "866": "VERB|r-advcl",
+    "867": "VERB|r-advmod",
+    "868": "VERB|r-appos",
+    "869": "VERB|r-case",
+    "870": "VERB|r-cc",
+    "871": "VERB|r-ccomp",
+    "872": "VERB|r-clf",
+    "873": "VERB|r-compound",
+    "874": "VERB|r-conj",
+    "875": "VERB|r-dep",
+    "876": "VERB|r-det",
+    "877": "VERB|r-discourse",
+    "878": "VERB|r-fixed",
+    "879": "VERB|r-flat",
+    "880": "VERB|r-list",
+    "881": "VERB|r-mark",
+    "882": "VERB|r-nmod",
+    "883": "VERB|r-nsubj",
+    "884": "VERB|r-obj",
+    "885": "VERB|r-obl",
+    "886": "VERB|r-orphan",
+    "887": "VERB|r-parataxis",
+    "888": "VERB|r-punct",
+    "889": "VERB|r-xcomp",
+    "890": "VERB|root"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "label2id": {
+    "ADP": 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|_": 9,
+    "ADP|l-acl": 10,
+    "ADP|l-advcl": 11,
+    "ADP|l-advmod": 12,
+    "ADP|l-case": 13,
+    "ADP|l-cc": 14,
+    "ADP|l-dep": 15,
+    "ADP|l-fixed": 16,
+    "ADP|l-flat": 17,
+    "ADP|l-mark": 18,
+    "ADP|l-nmod": 19,
+    "ADP|l-nsubj": 20,
+    "ADP|l-obl": 21,
+    "ADP|l-orphan": 22,
+    "ADP|r-acl": 23,
+    "ADP|r-advmod": 24,
+    "ADP|r-case": 25,
+    "ADP|r-compound": 26,
+    "ADP|r-conj": 27,
+    "ADP|r-fixed": 28,
+    "ADP|r-flat": 29,
+    "ADP|r-obl": 30,
+    "ADP|r-orphan": 31,
+    "ADP|root": 32,
+    "ADV": 33,
+    "ADV.": 34,
+    "ADV|Foreign=Yes|_": 35,
+    "ADV|Foreign=Yes|l-advmod": 36,
+    "ADV|Foreign=Yes|r-advmod": 37,
+    "ADV|NumType=Mult|_": 38,
+    "ADV|NumType=Mult|r-advmod": 39,
+    "ADV|PartType=Adv|_": 40,
+    "ADV|PartType=Adv|l-advmod": 41,
+    "ADV|PartType=Adv|l-mark": 42,
+    "ADV|PartType=Adv|r-advmod": 43,
+    "ADV|PartType=Enp|_": 44,
+    "ADV|PartType=Enp|l-advmod": 45,
+    "ADV|PartType=Enp|r-advmod": 46,
+    "ADV|PartType=Int|_": 47,
+    "ADV|PartType=Int|r-advmod": 48,
+    "ADV|PartType=Int|r-fixed": 49,
+    "ADV|Prefix=Yes|_": 50,
+    "ADV|Prefix=Yes|l-advmod": 51,
+    "ADV|Prefix=Yes|l-mark": 52,
+    "ADV|Prefix=Yes|r-advmod": 53,
+    "ADV|_": 54,
+    "ADV|l-acl": 55,
+    "ADV|l-advcl": 56,
+    "ADV|l-advmod": 57,
+    "ADV|l-aux": 58,
+    "ADV|l-case": 59,
+    "ADV|l-compound": 60,
+    "ADV|l-dep": 61,
+    "ADV|l-det": 62,
+    "ADV|l-discourse": 63,
+    "ADV|l-fixed": 64,
+    "ADV|l-mark": 65,
+    "ADV|l-orphan": 66,
+    "ADV|r-acl": 67,
+    "ADV|r-advcl": 68,
+    "ADV|r-advmod": 69,
+    "ADV|r-aux": 70,
+    "ADV|r-compound": 71,
+    "ADV|r-conj": 72,
+    "ADV|r-det": 73,
+    "ADV|r-fixed": 74,
+    "ADV|r-flat": 75,
+    "ADV|r-mark": 76,
+    "ADV|r-nmod": 77,
+    "ADV|r-obj": 78,
+    "ADV|r-orphan": 79,
+    "ADV|r-xcomp": 80,
+    "ADV|root": 81,
+    "AUX": 82,
+    "AUX.": 83,
+    "AUX|Foreign=Yes|_": 84,
+    "AUX|Foreign=Yes|l-aux": 85,
+    "AUX|NounType=Class|_": 86,
+    "AUX|NounType=Class|r-appos": 87,
+    "AUX|Prefix=Yes|_": 88,
+    "AUX|Prefix=Yes|l-aux": 89,
+    "AUX|Prefix=Yes|r-aux": 90,
+    "AUX|VerbType=Cop|_": 91,
+    "AUX|VerbType=Cop|l-acl": 92,
+    "AUX|VerbType=Cop|l-advcl": 93,
+    "AUX|VerbType=Cop|l-aux": 94,
+    "AUX|VerbType=Cop|l-cop": 95,
+    "AUX|VerbType=Cop|r-acl": 96,
+    "AUX|VerbType=Cop|r-advcl": 97,
+    "AUX|VerbType=Cop|r-aux": 98,
+    "AUX|VerbType=Cop|r-conj": 99,
+    "AUX|VerbType=Cop|r-mark": 100,
+    "AUX|VerbType=Cop|root": 101,
+    "AUX|_": 102,
+    "AUX|l-advmod": 103,
+    "AUX|l-aux": 104,
+    "AUX|l-cop": 105,
+    "AUX|l-mark": 106,
+    "AUX|r-acl": 107,
+    "AUX|r-advmod": 108,
+    "AUX|r-aux": 109,
+    "AUX|r-ccomp": 110,
+    "AUX|r-clf": 111,
+    "AUX|r-compound": 112,
+    "AUX|r-conj": 113,
+    "AUX|r-fixed": 114,
+    "AUX|root": 115,
+    "B-ADP": 116,
+    "B-ADP.": 117,
+    "B-ADV": 118,
+    "B-ADV.": 119,
+    "B-AUX": 120,
+    "B-AUX.": 121,
+    "B-CCONJ": 122,
+    "B-CCONJ.": 123,
+    "B-DET": 124,
+    "B-DET.": 125,
+    "B-NOUN": 126,
+    "B-NOUN.": 127,
+    "B-NUM": 128,
+    "B-NUM.": 129,
+    "B-PART": 130,
+    "B-PART.": 131,
+    "B-PRON": 132,
+    "B-PRON.": 133,
+    "B-PROPN": 134,
+    "B-PROPN.": 135,
+    "B-PUNCT": 136,
+    "B-PUNCT.": 137,
+    "B-SCONJ": 138,
+    "B-SCONJ.": 139,
+    "B-SYM": 140,
+    "B-SYM.": 141,
+    "B-VERB": 142,
+    "B-VERB.": 143,
+    "CCONJ": 144,
+    "CCONJ.": 145,
+    "CCONJ|Foreign=Yes|_": 146,
+    "CCONJ|Foreign=Yes|l-cc": 147,
+    "CCONJ|PronType=Prs|_": 148,
+    "CCONJ|PronType=Prs|l-cc": 149,
+    "CCONJ|_": 150,
+    "CCONJ|l-advmod": 151,
+    "CCONJ|l-case": 152,
+    "CCONJ|l-cc": 153,
+    "CCONJ|l-conj": 154,
+    "CCONJ|l-discourse": 155,
+    "CCONJ|l-fixed": 156,
+    "CCONJ|l-flat": 157,
+    "CCONJ|l-mark": 158,
+    "CCONJ|l-nsubj": 159,
+    "CCONJ|l-obj": 160,
+    "CCONJ|l-orphan": 161,
+    "CCONJ|r-cc": 162,
+    "CCONJ|r-compound": 163,
+    "CCONJ|r-fixed": 164,
+    "CCONJ|r-mark": 165,
+    "DET": 166,
+    "DET.": 167,
+    "DET|NumType=Mult|_": 168,
+    "DET|NumType=Mult|l-det": 169,
+    "DET|PartType=Emp|_": 170,
+    "DET|PartType=Emp|r-det": 171,
+    "DET|PartType=Int|_": 172,
+    "DET|PartType=Int|r-det": 173,
+    "DET|_": 174,
+    "DET|l-compound": 175,
+    "DET|l-det": 176,
+    "DET|l-discourse": 177,
+    "DET|l-nsubj": 178,
+    "DET|l-obl": 179,
+    "DET|l-orphan": 180,
+    "DET|r-advmod": 181,
+    "DET|r-compound": 182,
+    "DET|r-conj": 183,
+    "DET|r-dep": 184,
+    "DET|r-det": 185,
+    "DET|r-fixed": 186,
+    "DET|r-flat": 187,
+    "DET|r-list": 188,
+    "DET|r-nmod": 189,
+    "DET|r-nummod": 190,
+    "DET|r-obl": 191,
+    "DET|r-orphan": 192,
+    "I-ADP": 193,
+    "I-ADP.": 194,
+    "I-ADV": 195,
+    "I-ADV.": 196,
+    "I-AUX": 197,
+    "I-AUX.": 198,
+    "I-CCONJ": 199,
+    "I-CCONJ.": 200,
+    "I-DET": 201,
+    "I-DET.": 202,
+    "I-NOUN": 203,
+    "I-NOUN.": 204,
+    "I-NUM": 205,
+    "I-NUM.": 206,
+    "I-PART": 207,
+    "I-PART.": 208,
+    "I-PRON": 209,
+    "I-PRON.": 210,
+    "I-PROPN": 211,
+    "I-PROPN.": 212,
+    "I-PUNCT": 213,
+    "I-PUNCT.": 214,
+    "I-SCONJ": 215,
+    "I-SCONJ.": 216,
+    "I-SYM": 217,
+    "I-SYM.": 218,
+    "I-VERB": 219,
+    "I-VERB.": 220,
+    "NOUN": 221,
+    "NOUN.": 222,
+    "NOUN|Abbr=Yes|Foreign=Yes|_": 223,
+    "NOUN|Abbr=Yes|Foreign=Yes|r-nmod": 224,
+    "NOUN|Abbr=Yes|Prefix=Yes|_": 225,
+    "NOUN|Abbr=Yes|Prefix=Yes|l-flat": 226,
+    "NOUN|Abbr=Yes|_": 227,
+    "NOUN|Abbr=Yes|l-flat": 228,
+    "NOUN|Abbr=Yes|l-nmod": 229,
+    "NOUN|Abbr=Yes|l-nsubj": 230,
+    "NOUN|Abbr=Yes|l-obl": 231,
+    "NOUN|Abbr=Yes|r-acl": 232,
+    "NOUN|Abbr=Yes|r-appos": 233,
+    "NOUN|Abbr=Yes|r-clf": 234,
+    "NOUN|Abbr=Yes|r-conj": 235,
+    "NOUN|Abbr=Yes|r-fixed": 236,
+    "NOUN|Abbr=Yes|r-flat": 237,
+    "NOUN|Abbr=Yes|r-nmod": 238,
+    "NOUN|Abbr=Yes|r-obj": 239,
+    "NOUN|Abbr=Yes|r-obl": 240,
+    "NOUN|Foreign=Yes|NounType=Class|_": 241,
+    "NOUN|Foreign=Yes|NounType=Class|r-clf": 242,
+    "NOUN|Foreign=Yes|NounType=Class|r-obj": 243,
+    "NOUN|Foreign=Yes|Prefix=Yes|_": 244,
+    "NOUN|Foreign=Yes|Prefix=Yes|l-flat": 245,
+    "NOUN|Foreign=Yes|Prefix=Yes|r-appos": 246,
+    "NOUN|Foreign=Yes|_": 247,
+    "NOUN|Foreign=Yes|l-dislocated": 248,
+    "NOUN|Foreign=Yes|l-flat": 249,
+    "NOUN|Foreign=Yes|l-nmod": 250,
+    "NOUN|Foreign=Yes|l-nsubj": 251,
+    "NOUN|Foreign=Yes|l-obl": 252,
+    "NOUN|Foreign=Yes|r-acl": 253,
+    "NOUN|Foreign=Yes|r-advcl": 254,
+    "NOUN|Foreign=Yes|r-advmod": 255,
+    "NOUN|Foreign=Yes|r-appos": 256,
+    "NOUN|Foreign=Yes|r-ccomp": 257,
+    "NOUN|Foreign=Yes|r-clf": 258,
+    "NOUN|Foreign=Yes|r-compound": 259,
+    "NOUN|Foreign=Yes|r-conj": 260,
+    "NOUN|Foreign=Yes|r-flat": 261,
+    "NOUN|Foreign=Yes|r-iobj": 262,
+    "NOUN|Foreign=Yes|r-list": 263,
+    "NOUN|Foreign=Yes|r-nmod": 264,
+    "NOUN|Foreign=Yes|r-obj": 265,
+    "NOUN|Foreign=Yes|r-obl": 266,
+    "NOUN|Foreign=Yes|r-xcomp": 267,
+    "NOUN|Foreign=Yes|root": 268,
+    "NOUN|NameType=Com|_": 269,
+    "NOUN|NameType=Com|r-nmod": 270,
+    "NOUN|NameType=Geo|_": 271,
+    "NOUN|NameType=Geo|l-nsubj": 272,
+    "NOUN|NameType=Geo|r-nmod": 273,
+    "NOUN|NameType=Geo|r-obj": 274,
+    "NOUN|NameType=Nat|_": 275,
+    "NOUN|NameType=Nat|r-nmod": 276,
+    "NOUN|NameType=Oth|_": 277,
+    "NOUN|NameType=Oth|l-nsubj": 278,
+    "NOUN|NameType=Oth|r-conj": 279,
+    "NOUN|NameType=Oth|r-flat": 280,
+    "NOUN|NameType=Oth|r-nmod": 281,
+    "NOUN|NameType=Pro|_": 282,
+    "NOUN|NameType=Pro|r-nmod": 283,
+    "NOUN|NameType=Prs|_": 284,
+    "NOUN|NameType=Prs|l-nsubj": 285,
+    "NOUN|NameType=Prs|r-nmod": 286,
+    "NOUN|NounType=Class|Prefix=Yes|_": 287,
+    "NOUN|NounType=Class|Prefix=Yes|l-advcl": 288,
+    "NOUN|NounType=Class|Prefix=Yes|l-advmod": 289,
+    "NOUN|NounType=Class|Prefix=Yes|l-mark": 290,
+    "NOUN|NounType=Class|Prefix=Yes|l-nmod": 291,
+    "NOUN|NounType=Class|Prefix=Yes|l-nsubj": 292,
+    "NOUN|NounType=Class|Prefix=Yes|r-advcl": 293,
+    "NOUN|NounType=Class|Prefix=Yes|r-clf": 294,
+    "NOUN|NounType=Class|Prefix=Yes|r-nmod": 295,
+    "NOUN|NounType=Class|Prefix=Yes|r-obj": 296,
+    "NOUN|NounType=Class|_": 297,
+    "NOUN|NounType=Class|l-advcl": 298,
+    "NOUN|NounType=Class|l-advmod": 299,
+    "NOUN|NounType=Class|l-clf": 300,
+    "NOUN|NounType=Class|l-dislocated": 301,
+    "NOUN|NounType=Class|l-nmod": 302,
+    "NOUN|NounType=Class|l-nsubj": 303,
+    "NOUN|NounType=Class|l-obj": 304,
+    "NOUN|NounType=Class|l-obl": 305,
+    "NOUN|NounType=Class|r-acl": 306,
+    "NOUN|NounType=Class|r-advcl": 307,
+    "NOUN|NounType=Class|r-advmod": 308,
+    "NOUN|NounType=Class|r-appos": 309,
+    "NOUN|NounType=Class|r-cc": 310,
+    "NOUN|NounType=Class|r-ccomp": 311,
+    "NOUN|NounType=Class|r-clf": 312,
+    "NOUN|NounType=Class|r-compound": 313,
+    "NOUN|NounType=Class|r-conj": 314,
+    "NOUN|NounType=Class|r-dislocated": 315,
+    "NOUN|NounType=Class|r-fixed": 316,
+    "NOUN|NounType=Class|r-flat": 317,
+    "NOUN|NounType=Class|r-iobj": 318,
+    "NOUN|NounType=Class|r-list": 319,
+    "NOUN|NounType=Class|r-nmod": 320,
+    "NOUN|NounType=Class|r-nummod": 321,
+    "NOUN|NounType=Class|r-obj": 322,
+    "NOUN|NounType=Class|r-obl": 323,
+    "NOUN|NounType=Class|r-orphan": 324,
+    "NOUN|NounType=Class|r-xcomp": 325,
+    "NOUN|NounType=Class|root": 326,
+    "NOUN|NumType=Mult|_": 327,
+    "NOUN|NumType=Mult|r-advcl": 328,
+    "NOUN|NumType=Mult|r-nmod": 329,
+    "NOUN|NumType=Mult|r-obj": 330,
+    "NOUN|PartType=Enp|_": 331,
+    "NOUN|PartType=Enp|r-obj": 332,
+    "NOUN|PartType=Enp|r-obl": 333,
+    "NOUN|PartType=Int|_": 334,
+    "NOUN|PartType=Int|r-obj": 335,
+    "NOUN|PartType=Res|_": 336,
+    "NOUN|PartType=Res|r-nmod": 337,
+    "NOUN|PartType=Res|r-obj": 338,
+    "NOUN|Prefix=Yes|_": 339,
+    "NOUN|Prefix=Yes|l-acl": 340,
+    "NOUN|Prefix=Yes|l-advcl": 341,
+    "NOUN|Prefix=Yes|l-clf": 342,
+    "NOUN|Prefix=Yes|l-csubj": 343,
+    "NOUN|Prefix=Yes|l-dislocated": 344,
+    "NOUN|Prefix=Yes|l-flat": 345,
+    "NOUN|Prefix=Yes|l-nmod": 346,
+    "NOUN|Prefix=Yes|l-nsubj": 347,
+    "NOUN|Prefix=Yes|l-obj": 348,
+    "NOUN|Prefix=Yes|l-obl": 349,
+    "NOUN|Prefix=Yes|r-acl": 350,
+    "NOUN|Prefix=Yes|r-advcl": 351,
+    "NOUN|Prefix=Yes|r-advmod": 352,
+    "NOUN|Prefix=Yes|r-appos": 353,
+    "NOUN|Prefix=Yes|r-case": 354,
+    "NOUN|Prefix=Yes|r-cc": 355,
+    "NOUN|Prefix=Yes|r-ccomp": 356,
+    "NOUN|Prefix=Yes|r-clf": 357,
+    "NOUN|Prefix=Yes|r-compound": 358,
+    "NOUN|Prefix=Yes|r-conj": 359,
+    "NOUN|Prefix=Yes|r-dislocated": 360,
+    "NOUN|Prefix=Yes|r-fixed": 361,
+    "NOUN|Prefix=Yes|r-flat": 362,
+    "NOUN|Prefix=Yes|r-iobj": 363,
+    "NOUN|Prefix=Yes|r-list": 364,
+    "NOUN|Prefix=Yes|r-nmod": 365,
+    "NOUN|Prefix=Yes|r-nummod": 366,
+    "NOUN|Prefix=Yes|r-obj": 367,
+    "NOUN|Prefix=Yes|r-obl": 368,
+    "NOUN|Prefix=Yes|r-orphan": 369,
+    "NOUN|Prefix=Yes|r-xcomp": 370,
+    "NOUN|Prefix=Yes|root": 371,
+    "NOUN|_": 372,
+    "NOUN|l-acl": 373,
+    "NOUN|l-advcl": 374,
+    "NOUN|l-advmod": 375,
+    "NOUN|l-case": 376,
+    "NOUN|l-ccomp": 377,
+    "NOUN|l-compound": 378,
+    "NOUN|l-csubj": 379,
+    "NOUN|l-discourse": 380,
+    "NOUN|l-dislocated": 381,
+    "NOUN|l-expl": 382,
+    "NOUN|l-flat": 383,
+    "NOUN|l-iobj": 384,
+    "NOUN|l-mark": 385,
+    "NOUN|l-nmod": 386,
+    "NOUN|l-nsubj": 387,
+    "NOUN|l-nummod": 388,
+    "NOUN|l-obj": 389,
+    "NOUN|l-obl": 390,
+    "NOUN|l-orphan": 391,
+    "NOUN|l-vocative": 392,
+    "NOUN|r-acl": 393,
+    "NOUN|r-advcl": 394,
+    "NOUN|r-advmod": 395,
+    "NOUN|r-appos": 396,
+    "NOUN|r-case": 397,
+    "NOUN|r-cc": 398,
+    "NOUN|r-ccomp": 399,
+    "NOUN|r-clf": 400,
+    "NOUN|r-compound": 401,
+    "NOUN|r-conj": 402,
+    "NOUN|r-cop": 403,
+    "NOUN|r-discourse": 404,
+    "NOUN|r-dislocated": 405,
+    "NOUN|r-fixed": 406,
+    "NOUN|r-flat": 407,
+    "NOUN|r-iobj": 408,
+    "NOUN|r-list": 409,
+    "NOUN|r-mark": 410,
+    "NOUN|r-nmod": 411,
+    "NOUN|r-nsubj": 412,
+    "NOUN|r-nummod": 413,
+    "NOUN|r-obj": 414,
+    "NOUN|r-obl": 415,
+    "NOUN|r-orphan": 416,
+    "NOUN|r-parataxis": 417,
+    "NOUN|r-xcomp": 418,
+    "NOUN|root": 419,
+    "NUM": 420,
+    "NUM.": 421,
+    "NUM|Abbr=Yes|_": 422,
+    "NUM|Abbr=Yes|r-flat": 423,
+    "NUM|Abbr=Yes|r-nummod": 424,
+    "NUM|Abbr=Yes|r-obj": 425,
+    "NUM|Foreign=Yes|_": 426,
+    "NUM|Foreign=Yes|r-clf": 427,
+    "NUM|NumType=Mult|_": 428,
+    "NUM|NumType=Mult|l-advmod": 429,
+    "NUM|NumType=Mult|l-nummod": 430,
+    "NUM|NumType=Mult|r-advmod": 431,
+    "NUM|Prefix=Yes|_": 432,
+    "NUM|Prefix=Yes|l-nummod": 433,
+    "NUM|_": 434,
+    "NUM|l-advcl": 435,
+    "NUM|l-advmod": 436,
+    "NUM|l-case": 437,
+    "NUM|l-clf": 438,
+    "NUM|l-dep": 439,
+    "NUM|l-flat": 440,
+    "NUM|l-nmod": 441,
+    "NUM|l-nsubj": 442,
+    "NUM|l-nummod": 443,
+    "NUM|l-obl": 444,
+    "NUM|r-acl": 445,
+    "NUM|r-advmod": 446,
+    "NUM|r-appos": 447,
+    "NUM|r-ccomp": 448,
+    "NUM|r-compound": 449,
+    "NUM|r-conj": 450,
+    "NUM|r-det": 451,
+    "NUM|r-fixed": 452,
+    "NUM|r-flat": 453,
+    "NUM|r-iobj": 454,
+    "NUM|r-nmod": 455,
+    "NUM|r-nummod": 456,
+    "NUM|r-obj": 457,
+    "NUM|r-obl": 458,
+    "NUM|root": 459,
+    "PART": 460,
+    "PART.": 461,
+    "PART|NameType=Oth|_": 462,
+    "PART|NameType=Oth|l-advmod": 463,
+    "PART|NounType=Class|PartType=Emp|Prefix=Yes|_": 464,
+    "PART|NounType=Class|PartType=Emp|Prefix=Yes|l-mark": 465,
+    "PART|NounType=Class|PartType=Emp|_": 466,
+    "PART|NounType=Class|PartType=Emp|l-mark": 467,
+    "PART|NounType=Class|Prefix=Yes|_": 468,
+    "PART|NounType=Class|Prefix=Yes|l-mark": 469,
+    "PART|NumType=Mult|PartType=Emp|_": 470,
+    "PART|NumType=Mult|PartType=Emp|l-mark": 471,
+    "PART|PartType=Adj|_": 472,
+    "PART|PartType=Adj|l-mark": 473,
+    "PART|PartType=Adj|l-orphan": 474,
+    "PART|PartType=Adj|r-acl": 475,
+    "PART|PartType=Adj|r-compound": 476,
+    "PART|PartType=Adj|r-nmod": 477,
+    "PART|PartType=Adv|_": 478,
+    "PART|PartType=Adv|l-advmod": 479,
+    "PART|PartType=Adv|l-mark": 480,
+    "PART|PartType=Adv|r-advmod": 481,
+    "PART|PartType=Emp|Prefix=Yes|_": 482,
+    "PART|PartType=Emp|Prefix=Yes|l-advmod": 483,
+    "PART|PartType=Emp|Prefix=Yes|l-aux": 484,
+    "PART|PartType=Emp|Prefix=Yes|l-mark": 485,
+    "PART|PartType=Emp|_": 486,
+    "PART|PartType=Emp|l-advmod": 487,
+    "PART|PartType=Emp|l-case": 488,
+    "PART|PartType=Emp|l-discourse": 489,
+    "PART|PartType=Emp|l-mark": 490,
+    "PART|PartType=Emp|r-acl": 491,
+    "PART|PartType=Emp|r-advmod": 492,
+    "PART|PartType=Emp|r-aux": 493,
+    "PART|PartType=Emp|r-compound": 494,
+    "PART|PartType=Emp|r-det": 495,
+    "PART|PartType=Emp|r-fixed": 496,
+    "PART|PartType=Emp|r-mark": 497,
+    "PART|PartType=Emp|r-nmod": 498,
+    "PART|PartType=Enp|_": 499,
+    "PART|PartType=Enp|l-discourse": 500,
+    "PART|PartType=Enp|r-acl": 501,
+    "PART|PartType=Enp|r-advmod": 502,
+    "PART|PartType=Enp|r-compound": 503,
+    "PART|PartType=Enp|r-dep": 504,
+    "PART|PartType=Enp|r-det": 505,
+    "PART|PartType=Enp|r-discourse": 506,
+    "PART|PartType=Enp|r-fixed": 507,
+    "PART|PartType=Enp|r-obl": 508,
+    "PART|PartType=Int|_": 509,
+    "PART|PartType=Int|l-advmod": 510,
+    "PART|PartType=Int|l-mark": 511,
+    "PART|PartType=Int|r-acl": 512,
+    "PART|PartType=Int|r-advmod": 513,
+    "PART|PartType=Int|r-dep": 514,
+    "PART|PartType=Int|r-discourse": 515,
+    "PART|PartType=Int|r-nmod": 516,
+    "PART|PartType=Int|r-obj": 517,
+    "PART|PartType=Int|r-obl": 518,
+    "PART|PartType=Neg|_": 519,
+    "PART|PartType=Neg|l-advcl": 520,
+    "PART|PartType=Neg|l-advmod": 521,
+    "PART|PartType=Neg|l-aux": 522,
+    "PART|PartType=Neg|l-mark": 523,
+    "PART|PartType=Neg|r-acl": 524,
+    "PART|PartType=Neg|r-advmod": 525,
+    "PART|PartType=Neg|r-fixed": 526,
+    "PART|PartType=Res|_": 527,
+    "PART|PartType=Res|r-advmod": 528,
+    "PART|PartType=Res|r-discourse": 529,
+    "PART|PartType=Res|r-fixed": 530,
+    "PART|Prefix=Yes|_": 531,
+    "PART|Prefix=Yes|l-advmod": 532,
+    "PART|Prefix=Yes|l-aux": 533,
+    "PART|Prefix=Yes|l-mark": 534,
+    "PART|Prefix=Yes|r-acl": 535,
+    "PART|Prefix=Yes|r-nmod": 536,
+    "PART|_": 537,
+    "PART|l-advmod": 538,
+    "PART|l-discourse": 539,
+    "PART|l-mark": 540,
+    "PART|l-nsubj": 541,
+    "PART|r-acl": 542,
+    "PART|r-advmod": 543,
+    "PART|r-discourse": 544,
+    "PART|r-fixed": 545,
+    "PART|r-mark": 546,
+    "PART|r-obj": 547,
+    "PRON": 548,
+    "PRON.": 549,
+    "PRON|NounType=Class|_": 550,
+    "PRON|NounType=Class|r-clf": 551,
+    "PRON|PronType=Prs|_": 552,
+    "PRON|PronType=Prs|l-advmod": 553,
+    "PRON|PronType=Prs|l-expl": 554,
+    "PRON|PronType=Prs|l-nsubj": 555,
+    "PRON|PronType=Prs|l-obj": 556,
+    "PRON|PronType=Prs|l-obl": 557,
+    "PRON|PronType=Prs|r-advcl": 558,
+    "PRON|PronType=Prs|r-advmod": 559,
+    "PRON|PronType=Prs|r-ccomp": 560,
+    "PRON|PronType=Prs|r-clf": 561,
+    "PRON|PronType=Prs|r-conj": 562,
+    "PRON|PronType=Prs|r-nmod": 563,
+    "PRON|PronType=Prs|r-nsubj": 564,
+    "PRON|PronType=Prs|r-obj": 565,
+    "PRON|PronType=Prs|r-obl": 566,
+    "PRON|PronType=Prs|root": 567,
+    "PRON|PronType=Rcp|_": 568,
+    "PRON|PronType=Rcp|r-advmod": 569,
+    "PRON|PronType=Rcp|r-iobj": 570,
+    "PRON|PronType=Rcp|r-nmod": 571,
+    "PRON|PronType=Rcp|r-obj": 572,
+    "PRON|PronType=Rcp|r-obl": 573,
+    "PRON|_": 574,
+    "PRON|l-advcl": 575,
+    "PRON|l-advmod": 576,
+    "PRON|l-compound": 577,
+    "PRON|l-csubj": 578,
+    "PRON|l-dislocated": 579,
+    "PRON|l-expl": 580,
+    "PRON|l-iobj": 581,
+    "PRON|l-mark": 582,
+    "PRON|l-nsubj": 583,
+    "PRON|l-obj": 584,
+    "PRON|l-obl": 585,
+    "PRON|r-acl": 586,
+    "PRON|r-advmod": 587,
+    "PRON|r-appos": 588,
+    "PRON|r-ccomp": 589,
+    "PRON|r-compound": 590,
+    "PRON|r-conj": 591,
+    "PRON|r-det": 592,
+    "PRON|r-discourse": 593,
+    "PRON|r-fixed": 594,
+    "PRON|r-flat": 595,
+    "PRON|r-iobj": 596,
+    "PRON|r-nmod": 597,
+    "PRON|r-nsubj": 598,
+    "PRON|r-obj": 599,
+    "PRON|r-obl": 600,
+    "PROPN": 601,
+    "PROPN.": 602,
+    "PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth|_": 603,
+    "PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth|r-obj": 604,
+    "PROPN|Abbr=Yes|NameType=Com|_": 605,
+    "PROPN|Abbr=Yes|NameType=Com|r-advmod": 606,
+    "PROPN|Abbr=Yes|NameType=Com|r-nmod": 607,
+    "PROPN|Abbr=Yes|_": 608,
+    "PROPN|Abbr=Yes|l-nmod": 609,
+    "PROPN|Abbr=Yes|l-nsubj": 610,
+    "PROPN|Abbr=Yes|r-nmod": 611,
+    "PROPN|Foreign=Yes|NameType=Com|_": 612,
+    "PROPN|Foreign=Yes|NameType=Com|l-nsubj": 613,
+    "PROPN|Foreign=Yes|NameType=Com|r-list": 614,
+    "PROPN|Foreign=Yes|NameType=Com|r-nmod": 615,
+    "PROPN|Foreign=Yes|NameType=Com|r-obl": 616,
+    "PROPN|Foreign=Yes|NameType=Geo|_": 617,
+    "PROPN|Foreign=Yes|NameType=Geo|r-obj": 618,
+    "PROPN|Foreign=Yes|NameType=Geo|r-obl": 619,
+    "PROPN|Foreign=Yes|NameType=Giv|_": 620,
+    "PROPN|Foreign=Yes|NameType=Giv|l-nsubj": 621,
+    "PROPN|Foreign=Yes|NameType=Oth|_": 622,
+    "PROPN|Foreign=Yes|NameType=Oth|r-conj": 623,
+    "PROPN|Foreign=Yes|NameType=Oth|r-flat": 624,
+    "PROPN|Foreign=Yes|NameType=Oth|r-nmod": 625,
+    "PROPN|Foreign=Yes|NameType=Prs|_": 626,
+    "PROPN|Foreign=Yes|NameType=Prs|l-flat": 627,
+    "PROPN|Foreign=Yes|NameType=Prs|l-nsubj": 628,
+    "PROPN|Foreign=Yes|NameType=Prs|r-conj": 629,
+    "PROPN|Foreign=Yes|NameType=Prs|r-flat": 630,
+    "PROPN|Foreign=Yes|NameType=Prs|r-nmod": 631,
+    "PROPN|Foreign=Yes|NameType=Prs|r-obj": 632,
+    "PROPN|Foreign=Yes|NameType=Prs|r-obl": 633,
+    "PROPN|Foreign=Yes|NameType=Sur|_": 634,
+    "PROPN|Foreign=Yes|NameType=Sur|r-flat": 635,
+    "PROPN|Foreign=Yes|_": 636,
+    "PROPN|Foreign=Yes|l-flat": 637,
+    "PROPN|Foreign=Yes|l-nmod": 638,
+    "PROPN|Foreign=Yes|l-nsubj": 639,
+    "PROPN|Foreign=Yes|l-obl": 640,
+    "PROPN|Foreign=Yes|r-appos": 641,
+    "PROPN|Foreign=Yes|r-ccomp": 642,
+    "PROPN|Foreign=Yes|r-compound": 643,
+    "PROPN|Foreign=Yes|r-conj": 644,
+    "PROPN|Foreign=Yes|r-flat": 645,
+    "PROPN|Foreign=Yes|r-iobj": 646,
+    "PROPN|Foreign=Yes|r-list": 647,
+    "PROPN|Foreign=Yes|r-nmod": 648,
+    "PROPN|Foreign=Yes|r-nsubj": 649,
+    "PROPN|Foreign=Yes|r-obj": 650,
+    "PROPN|Foreign=Yes|r-obl": 651,
+    "PROPN|Foreign=Yes|root": 652,
+    "PROPN|NameType=Com|_": 653,
+    "PROPN|NameType=Com|l-nsubj": 654,
+    "PROPN|NameType=Com|l-obl": 655,
+    "PROPN|NameType=Com|r-appos": 656,
+    "PROPN|NameType=Com|r-conj": 657,
+    "PROPN|NameType=Com|r-flat": 658,
+    "PROPN|NameType=Com|r-list": 659,
+    "PROPN|NameType=Com|r-nmod": 660,
+    "PROPN|NameType=Com|r-nsubj": 661,
+    "PROPN|NameType=Com|r-obj": 662,
+    "PROPN|NameType=Com|r-obl": 663,
+    "PROPN|NameType=Geo|_": 664,
+    "PROPN|NameType=Geo|l-nsubj": 665,
+    "PROPN|NameType=Geo|l-obl": 666,
+    "PROPN|NameType=Geo|r-compound": 667,
+    "PROPN|NameType=Geo|r-conj": 668,
+    "PROPN|NameType=Geo|r-flat": 669,
+    "PROPN|NameType=Geo|r-list": 670,
+    "PROPN|NameType=Geo|r-nmod": 671,
+    "PROPN|NameType=Geo|r-nsubj": 672,
+    "PROPN|NameType=Geo|r-nummod": 673,
+    "PROPN|NameType=Geo|r-obj": 674,
+    "PROPN|NameType=Geo|r-obl": 675,
+    "PROPN|NameType=Geo|root": 676,
+    "PROPN|NameType=Giv|_": 677,
+    "PROPN|NameType=Giv|l-dislocated": 678,
+    "PROPN|NameType=Giv|l-nsubj": 679,
+    "PROPN|NameType=Giv|l-obl": 680,
+    "PROPN|NameType=Giv|r-acl": 681,
+    "PROPN|NameType=Giv|r-appos": 682,
+    "PROPN|NameType=Giv|r-ccomp": 683,
+    "PROPN|NameType=Giv|r-conj": 684,
+    "PROPN|NameType=Giv|r-flat": 685,
+    "PROPN|NameType=Giv|r-list": 686,
+    "PROPN|NameType=Giv|r-nmod": 687,
+    "PROPN|NameType=Giv|r-nsubj": 688,
+    "PROPN|NameType=Giv|r-obj": 689,
+    "PROPN|NameType=Giv|r-obl": 690,
+    "PROPN|NameType=Giv|root": 691,
+    "PROPN|NameType=Nat|_": 692,
+    "PROPN|NameType=Nat|l-csubj": 693,
+    "PROPN|NameType=Nat|l-nsubj": 694,
+    "PROPN|NameType=Nat|l-obl": 695,
+    "PROPN|NameType=Nat|r-acl": 696,
+    "PROPN|NameType=Nat|r-appos": 697,
+    "PROPN|NameType=Nat|r-compound": 698,
+    "PROPN|NameType=Nat|r-conj": 699,
+    "PROPN|NameType=Nat|r-flat": 700,
+    "PROPN|NameType=Nat|r-list": 701,
+    "PROPN|NameType=Nat|r-nmod": 702,
+    "PROPN|NameType=Nat|r-nummod": 703,
+    "PROPN|NameType=Nat|r-obj": 704,
+    "PROPN|NameType=Nat|r-obl": 705,
+    "PROPN|NameType=Oth|_": 706,
+    "PROPN|NameType=Oth|l-dislocated": 707,
+    "PROPN|NameType=Oth|l-nsubj": 708,
+    "PROPN|NameType=Oth|r-acl": 709,
+    "PROPN|NameType=Oth|r-appos": 710,
+    "PROPN|NameType=Oth|r-compound": 711,
+    "PROPN|NameType=Oth|r-conj": 712,
+    "PROPN|NameType=Oth|r-flat": 713,
+    "PROPN|NameType=Oth|r-nmod": 714,
+    "PROPN|NameType=Oth|r-obj": 715,
+    "PROPN|NameType=Oth|r-obl": 716,
+    "PROPN|NameType=Oth|root": 717,
+    "PROPN|NameType=Pro|_": 718,
+    "PROPN|NameType=Pro|l-nsubj": 719,
+    "PROPN|NameType=Pro|l-obl": 720,
+    "PROPN|NameType=Pro|r-advcl": 721,
+    "PROPN|NameType=Pro|r-flat": 722,
+    "PROPN|NameType=Pro|r-nmod": 723,
+    "PROPN|NameType=Pro|r-obj": 724,
+    "PROPN|NameType=Prs|_": 725,
+    "PROPN|NameType=Prs|l-dislocated": 726,
+    "PROPN|NameType=Prs|l-nsubj": 727,
+    "PROPN|NameType=Prs|l-obl": 728,
+    "PROPN|NameType=Prs|l-vocative": 729,
+    "PROPN|NameType=Prs|r-conj": 730,
+    "PROPN|NameType=Prs|r-discourse": 731,
+    "PROPN|NameType=Prs|r-flat": 732,
+    "PROPN|NameType=Prs|r-list": 733,
+    "PROPN|NameType=Prs|r-nmod": 734,
+    "PROPN|NameType=Prs|r-obj": 735,
+    "PROPN|NameType=Prs|r-obl": 736,
+    "PROPN|NameType=Prs|r-vocative": 737,
+    "PROPN|NameType=Sur|_": 738,
+    "PROPN|NameType=Sur|l-nsubj": 739,
+    "PROPN|NameType=Sur|r-flat": 740,
+    "PROPN|NameType=Sur|r-nmod": 741,
+    "PROPN|NounType=Class|_": 742,
+    "PROPN|NounType=Class|r-clf": 743,
+    "PROPN|Prefix=Yes|_": 744,
+    "PROPN|Prefix=Yes|l-nsubj": 745,
+    "PROPN|Prefix=Yes|r-nmod": 746,
+    "PROPN|_": 747,
+    "PROPN|l-advmod": 748,
+    "PROPN|l-nsubj": 749,
+    "PROPN|l-obl": 750,
+    "PROPN|r-acl": 751,
+    "PROPN|r-advmod": 752,
+    "PROPN|r-appos": 753,
+    "PROPN|r-clf": 754,
+    "PROPN|r-compound": 755,
+    "PROPN|r-conj": 756,
+    "PROPN|r-fixed": 757,
+    "PROPN|r-flat": 758,
+    "PROPN|r-iobj": 759,
+    "PROPN|r-list": 760,
+    "PROPN|r-nmod": 761,
+    "PROPN|r-obj": 762,
+    "PROPN|r-obl": 763,
+    "PROPN|root": 764,
+    "PUNCT": 765,
+    "PUNCT.": 766,
+    "PUNCT|NounType=Class|_": 767,
+    "PUNCT|NounType=Class|r-punct": 768,
+    "PUNCT|_": 769,
+    "PUNCT|l-advmod": 770,
+    "PUNCT|l-dep": 771,
+    "PUNCT|l-punct": 772,
+    "PUNCT|r-dep": 773,
+    "PUNCT|r-punct": 774,
+    "SCONJ": 775,
+    "SCONJ.": 776,
+    "SCONJ|NumType=Mult|_": 777,
+    "SCONJ|NumType=Mult|l-mark": 778,
+    "SCONJ|Prefix=Yes|_": 779,
+    "SCONJ|Prefix=Yes|l-cc": 780,
+    "SCONJ|Prefix=Yes|l-mark": 781,
+    "SCONJ|VerbType=Cop|_": 782,
+    "SCONJ|VerbType=Cop|l-mark": 783,
+    "SCONJ|_": 784,
+    "SCONJ|l-advmod": 785,
+    "SCONJ|l-case": 786,
+    "SCONJ|l-cc": 787,
+    "SCONJ|l-discourse": 788,
+    "SCONJ|l-mark": 789,
+    "SCONJ|l-nsubj": 790,
+    "SCONJ|l-orphan": 791,
+    "SCONJ|r-advcl": 792,
+    "SCONJ|r-compound": 793,
+    "SCONJ|r-fixed": 794,
+    "SCONJ|r-flat": 795,
+    "SCONJ|r-mark": 796,
+    "SCONJ|r-orphan": 797,
+    "SCONJ|root": 798,
+    "SYM": 799,
+    "SYM.": 800,
+    "SYM|_": 801,
+    "SYM|l-dep": 802,
+    "SYM|r-clf": 803,
+    "SYM|r-nmod": 804,
+    "SYM|r-obj": 805,
+    "SYM|r-obl": 806,
+    "SYM|r-xcomp": 807,
+    "VERB": 808,
+    "VERB.": 809,
+    "VERB|Abbr=Yes|_": 810,
+    "VERB|Abbr=Yes|r-acl": 811,
+    "VERB|Foreign=Yes|_": 812,
+    "VERB|Foreign=Yes|l-nsubj": 813,
+    "VERB|Foreign=Yes|r-acl": 814,
+    "VERB|Foreign=Yes|r-advcl": 815,
+    "VERB|Foreign=Yes|r-ccomp": 816,
+    "VERB|Foreign=Yes|r-compound": 817,
+    "VERB|Foreign=Yes|r-conj": 818,
+    "VERB|Foreign=Yes|r-flat": 819,
+    "VERB|Foreign=Yes|r-nmod": 820,
+    "VERB|Foreign=Yes|r-xcomp": 821,
+    "VERB|Foreign=Yes|root": 822,
+    "VERB|NounType=Class|_": 823,
+    "VERB|NounType=Class|r-acl": 824,
+    "VERB|NounType=Class|r-compound": 825,
+    "VERB|PartType=Adj|_": 826,
+    "VERB|PartType=Adj|r-acl": 827,
+    "VERB|Prefix=Yes|_": 828,
+    "VERB|Prefix=Yes|l-acl": 829,
+    "VERB|Prefix=Yes|l-nsubj": 830,
+    "VERB|Prefix=Yes|r-acl": 831,
+    "VERB|Prefix=Yes|r-advcl": 832,
+    "VERB|Prefix=Yes|r-ccomp": 833,
+    "VERB|Prefix=Yes|r-compound": 834,
+    "VERB|Prefix=Yes|r-conj": 835,
+    "VERB|Prefix=Yes|r-parataxis": 836,
+    "VERB|Prefix=Yes|root": 837,
+    "VERB|VerbType=Cop|_": 838,
+    "VERB|VerbType=Cop|l-advmod": 839,
+    "VERB|VerbType=Cop|l-cop": 840,
+    "VERB|VerbType=Cop|r-acl": 841,
+    "VERB|VerbType=Cop|r-advcl": 842,
+    "VERB|VerbType=Cop|r-ccomp": 843,
+    "VERB|VerbType=Cop|r-compound": 844,
+    "VERB|VerbType=Cop|r-parataxis": 845,
+    "VERB|VerbType=Cop|root": 846,
+    "VERB|_": 847,
+    "VERB|l-acl": 848,
+    "VERB|l-advcl": 849,
+    "VERB|l-advmod": 850,
+    "VERB|l-case": 851,
+    "VERB|l-cc": 852,
+    "VERB|l-ccomp": 853,
+    "VERB|l-compound": 854,
+    "VERB|l-conj": 855,
+    "VERB|l-cop": 856,
+    "VERB|l-csubj": 857,
+    "VERB|l-discourse": 858,
+    "VERB|l-dislocated": 859,
+    "VERB|l-mark": 860,
+    "VERB|l-nsubj": 861,
+    "VERB|l-obl": 862,
+    "VERB|l-orphan": 863,
+    "VERB|l-xcomp": 864,
+    "VERB|r-acl": 865,
+    "VERB|r-advcl": 866,
+    "VERB|r-advmod": 867,
+    "VERB|r-appos": 868,
+    "VERB|r-case": 869,
+    "VERB|r-cc": 870,
+    "VERB|r-ccomp": 871,
+    "VERB|r-clf": 872,
+    "VERB|r-compound": 873,
+    "VERB|r-conj": 874,
+    "VERB|r-dep": 875,
+    "VERB|r-det": 876,
+    "VERB|r-discourse": 877,
+    "VERB|r-fixed": 878,
+    "VERB|r-flat": 879,
+    "VERB|r-list": 880,
+    "VERB|r-mark": 881,
+    "VERB|r-nmod": 882,
+    "VERB|r-nsubj": 883,
+    "VERB|r-obj": 884,
+    "VERB|r-obl": 885,
+    "VERB|r-orphan": 886,
+    "VERB|r-parataxis": 887,
+    "VERB|r-punct": 888,
+    "VERB|r-xcomp": 889,
+    "VERB|root": 890
+  },
+  "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": "4.48.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

maker.py

@@ -0,0 +1,120 @@
+#! /usr/bin/python3
+src="scb10x/llama3.2-typhoon2-1b"
+tgt="KoichiYasuoka/llama3.2-typhoon2-1b-ud-embeds"
+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 UDEmbedsDataset(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.seeks=[0]
+    label=set(["SYM","SYM.","SYM|_"])
+    dep=set()
+    s=self.conllu.readline()
+    while s!="":
+      if s=="\n":
+        self.seeks.append(self.conllu.tell())
+      else:
+        w=s.split("\t")
+        if len(w)==10:
+          if w[0].isdecimal():
+            p=w[3]
+            q="" if w[5]=="_" else "|"+w[5]
+            d=("|" if w[6]=="0" else "|l-" if int(w[0])<int(w[6]) else "|r-")+w[7]
+            for k in [p,p+".","B-"+p,"B-"+p+".","I-"+p,"I-"+p+".",p+q+"|_",p+q+d]:
+              label.add(k)
+      s=self.conllu.readline()
+    self.label2id={l:i for i,l in enumerate(sorted(label))}
+  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):
+    import torch
+    self.conllu.seek(self.seeks[i])
+    c,t,s=[],[""],False
+    while t[0]!="\n":
+      t=self.conllu.readline().split("\t") 
+      if len(t)==10 and t[0].isdecimal():
+        if s:
+           t[1]=" "+t[1]
+        c.append(t)
+        s=t[9].find("SpaceAfter=No")<0
+    x=[True if t[6]=="0" or int(t[6])>j or sum([1 if int(c[i][6])==j+1 else 0 for i in range(j+1,len(c))])>0 else False for j,t in enumerate(c)]
+    v=self.tokenizer([t[1] for t in c],add_special_tokens=False)["input_ids"]
+    ids,upos=[self.tokenizer.bos_token_id],["SYM."]
+    for i,(j,k) in enumerate(zip(v,c)):
+      if j==[]:
+        j=[self.tokenizer.unk_token_id]
+      p=k[3] if x[i] else k[3]+"."
+      ids+=j
+      upos+=[p] if len(j)==1 else ["B-"+p]+["I-"+p]*(len(j)-1)
+    x=[True if t[6]=="0" or int(t[6])>j or sum([1 if int(c[i][6])==j+1 else 0 for i in range(j+1,len(c))])>0 else False for j,t in enumerate(c)]
+    if len(x)<88:
+      x=[True]*len(x)
+      w=(len(x)+1)*(len(x)+2)/2+len(ids)
+    else:
+      w=sum([len(x)-i+1 if b else 0 for i,b in enumerate(x)])+len(ids)+1
+      for i in range(len(x)):
+        if x[i]==False and w+len(x)-i<4096:
+          x[i]=True
+          w+=len(x)-i+1
+    v=self.oldtokenizer([t[1] for t in c],add_special_tokens=False)["input_ids"]
+    p=[t[3] if t[5]=="_" else t[3]+"|"+t[5] for i,t in enumerate(c)]
+    d=[t[7] if t[6]=="0" else "l-"+t[7] if int(t[0])<int(t[6]) else "r-"+t[7] for t in c]
+    idx=[-1]
+    upos.append("SYM|_")
+    for i in range(len(x)):
+      if x[i]:
+        idx.append(i)
+        upos.append(p[i]+"|"+d[i] if c[i][6]=="0" else p[i]+"|_")
+        for j in range(i+1,len(x)):
+          idx.append(j)
+          upos.append(p[j]+"|"+d[j] if int(c[j][6])==i+1 else p[i]+"|"+d[i] if int(c[i][6])==j+1 else p[j]+"|_")
+        if i>0 and w>4096:
+          while w>4096:
+            if upos[-1].endswith("|_"):
+              upos.pop(-1)
+              idx.pop(-1)
+              w-=1
+            else:
+              break
+        idx.append(-1)
+        upos.append("SYM|_")
+    with torch.no_grad():
+      m=[]
+      for j in v:
+        if j==[]:
+          j=[self.tokenizer.convert_tokens_to_ids("<|python_tag|>")]
+        m.append(self.embeddings[j,:].sum(axis=0))
+      m.append(self.embeddings[self.tokenizer.eos_token_id])
+      emb=torch.stack(m)
+    return{"inputs_embeds":torch.vstack((self.embeddings[ids,:],emb[idx,:])),"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)
+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=UDEmbedsDataset("train.conllu",ntk,otk)
+devDS=UDEmbedsDataset("dev.conllu",ntk,otk)
+testDS=UDEmbedsDataset("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,trust_remote_code=True)
+mdl=AutoModelForTokenClassification.from_pretrained(src,config=cfg,ignore_mismatched_sizes=True,trust_remote_code=True)
+trainDS.embeddings=mdl.get_input_embeddings().weight
+arg=TrainingArguments(num_train_epochs=3,per_device_train_batch_size=1,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 sha256:36264c29142b869354148d72bdaa3f30b0d208bdd962ef3a18dec7b2e5a8f080
+size 4950610458

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "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,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

ud.py

@@ -0,0 +1,159 @@
+import numpy
+from transformers import TokenClassificationPipeline
+
+class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
+  def __init__(self,**kwargs):
+    from copy import deepcopy
+    from tokenizers import Regex
+    from tokenizers.pre_tokenizers import Sequence,Split,Whitespace
+    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.find("|")<0 and not k.startswith("I-")]
+    self.transition=numpy.full((len(x),len(x)),-numpy.inf)
+    for k,v in x.items():
+      if k.find("|")<0:
+        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)
+    return self.bellman_ford_token_classification(model_outputs,**kwargs)
+  def bellman_ford_token_classification(self,model_outputs,**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.max(m[i]+self.transition,axis=1)
+    k=[numpy.argmax(m[0]+self.transition[0])]
+    for i in range(1,m.shape[0]):
+      k.append(numpy.argmax(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 i>0 and w[i-1]["end"]>t["start"]:
+          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 UniversalDependenciesPipeline(BellmanFordTokenClassificationPipeline):
+  def __init__(self,**kwargs):
+    kwargs["aggregation_strategy"]="simple"
+    super().__init__(**kwargs)
+    x=self.model.config.label2id
+    self.root=numpy.full((len(x)),-numpy.inf)
+    self.left_arc=numpy.full((len(x)),-numpy.inf)
+    self.right_arc=numpy.full((len(x)),-numpy.inf)
+    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
+    kwargs["aggregation_strategy"]="simple"
+    if "logits" not in model_outputs:
+      return self.postprocess(model_outputs[0],**kwargs)
+    w=self.bellman_ford_token_classification(model_outputs,**kwargs)
+    off=[(t["start"],t["end"]) for t in w]
+    for i,(s,e) in reversed(list(enumerate(off))):
+      if s<e:
+        d=w[i]["text"]
+        j=len(d)-len(d.lstrip())
+        if j>0:
+          d=d.lstrip()
+          off[i]=(off[i][0]+j,off[i][1])
+        j=len(d)-len(d.rstrip())
+        if j>0:
+          d=d.rstrip()
+          off[i]=(off[i][0],off[i][1]-j)
+        if d.strip()=="":
+          off.pop(i)
+          w.pop(i)
+    v=self.oldtokenizer([t["text"] for t in w],add_special_tokens=False)
+    x=[not t["entity_group"].endswith(".") for t in w]
+    z=model_outputs["input_ids"][0]
+    if len(x)<510:
+      x=[True]*len(x)
+    else:
+      k=sum([len(x)-i+1 if b else 0 for i,b in enumerate(x)])+len(z)+1
+      for i in numpy.argsort(numpy.array([t["score"] for t in w])):
+        if x[i]==False and k+len(x)-i<131072:
+          x[i]=True
+          k+=len(x)-i+1
+    ids=[-1]
+    for i in range(len(x)):
+      if x[i]:
+        ids.append(i)
+        for j in range(i+1,len(x)):
+          ids.append(j)
+        ids.append(-1)
+    with torch.no_grad():
+      e=self.model.get_input_embeddings().weight
+      m=[]
+      for j in v["input_ids"]:
+        if j==[]:
+          j=[self.tokenizer.convert_tokens_to_ids("<|python_tag|>")]
+        m.append(e[j,:].sum(axis=0))
+      m.append(e[self.tokenizer.eos_token_id,:])
+      m=torch.stack(m).to(self.device)
+      e=self.model(inputs_embeds=torch.unsqueeze(torch.vstack((e[z,:],m[ids,:])),0))
+    m=e.logits[0].cpu().numpy()
+    e=numpy.full((len(x),len(x),m.shape[-1]),m.min())
+    k=len(z)+1
+    for i in range(len(x)):
+      if x[i]:
+        e[i,i]=m[k]+self.root
+        k+=1
+        for j in range(1,len(x)-i):
+          e[i+j,i]=m[k]+self.left_arc
+          e[i,i+j]=m[k]+self.right_arc
+          k+=1
+        k+=1
+    m,p=numpy.max(e,axis=2),numpy.argmax(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.argmax(m[z,z])],numpy.min(m)-numpy.max(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,(s,e) in enumerate(off):
+      u+="\t".join([str(i+1),t[s:e],"_",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(off) and e<off[i+1][0] else "SpaceAfter=No"])+"\n"
+    return u+"\n"
+  def chu_liu_edmonds(self,matrix):
+    h=numpy.argmax(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.max(matrix,axis=0)
+    m=numpy.block([[z[x,:][:,x],numpy.max(z[x,:][:,y],axis=1).reshape(len(x),1)],[numpy.max(z[y,:][:,x],axis=0),numpy.max(z[y,y])]])
+    k=[j if i==len(x) else x[j] if j<len(x) else y[numpy.argmax(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.argmax(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