initial release

Browse files

Files changed (8) hide show

README.md +27 -3
config.json +559 -0
pytorch_model.bin +3 -0
sentencepiece.bpe.model +3 -0
special_tokens_map.json +1 -0
supar.model +3 -0
tokenizer.json +0 -0
tokenizer_config.json +1 -0

README.md CHANGED Viewed

@@ -1,3 +1,27 @@
----
-license: cc-by-sa-4.0
----

+---
+language:
+- "en"
+tags:
+- "english"
+- "token-classification"
+- "pos"
+datasets:
+- "universal_dependencies"
+license: "cc-by-sa-4.0"
+pipeline_tag: "token-classification"
+---
+# xlm-roberta-base-english-upos
+## Model Description
+This is a XLM-RoBERTa model pre-trained on English corpus for POS-tagging, derived from [xlm-roberta-base](https://huggingface.co/xlm-roberta-base). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
+## How to Use
+```py
+from transformers import AutoTokenizer,AutoModelForTokenClassification
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/xlm-roberta-base-english-upos")
+model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/xlm-roberta-base-english-upos")
+```

config.json ADDED Viewed

	@@ -0,0 +1,559 @@

+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADJ+PART",
+    "2": "ADP",
+    "3": "ADV",
+    "4": "ADV+PART",
+    "5": "AUX",
+    "6": "AUX+PART",
+    "7": "B-ADJ",
+    "8": "B-ADJ+PART",
+    "9": "B-ADP",
+    "10": "B-ADP+ADP",
+    "11": "B-ADV",
+    "12": "B-AUX",
+    "13": "B-AUX+PART",
+    "14": "B-AUX+PART+VERB",
+    "15": "B-CCONJ",
+    "16": "B-DET",
+    "17": "B-INTJ",
+    "18": "B-NOUN",
+    "19": "B-NOUN+PART",
+    "20": "B-NUM",
+    "21": "B-PART",
+    "22": "B-PRON",
+    "23": "B-PRON+AUX",
+    "24": "B-PROPN",
+    "25": "B-PROPN+PART",
+    "26": "B-PUNCT",
+    "27": "B-SCONJ",
+    "28": "B-SYM",
+    "29": "B-VERB",
+    "30": "B-VERB+ADV",
+    "31": "B-VERB+PART",
+    "32": "B-X",
+    "33": "CCONJ",
+    "34": "DET",
+    "35": "I-ADJ",
+    "36": "I-ADJ+PART",
+    "37": "I-ADP",
+    "38": "I-ADP+ADP",
+    "39": "I-ADV",
+    "40": "I-AUX",
+    "41": "I-AUX+PART",
+    "42": "I-AUX+PART+VERB",
+    "43": "I-CCONJ",
+    "44": "I-DET",
+    "45": "I-INTJ",
+    "46": "I-NOUN",
+    "47": "I-NOUN+PART",
+    "48": "I-NUM",
+    "49": "I-PART",
+    "50": "I-PRON",
+    "51": "I-PRON+AUX",
+    "52": "I-PROPN",
+    "53": "I-PROPN+PART",
+    "54": "I-PUNCT",
+    "55": "I-SCONJ",
+    "56": "I-SYM",
+    "57": "I-VERB",
+    "58": "I-VERB+ADV",
+    "59": "I-VERB+PART",
+    "60": "I-X",
+    "61": "INTJ",
+    "62": "NOUN",
+    "63": "NOUN+ADP",
+    "64": "NOUN+PART",
+    "65": "NUM",
+    "66": "PART",
+    "67": "PRON",
+    "68": "PRON+AUX",
+    "69": "PRON+VERB",
+    "70": "PROPN",
+    "71": "PUNCT",
+    "72": "SCONJ",
+    "73": "SYM",
+    "74": "VERB",
+    "75": "VERB+PART",
+    "76": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADJ": 0,
+    "ADJ+PART": 1,
+    "ADP": 2,
+    "ADV": 3,
+    "ADV+PART": 4,
+    "AUX": 5,
+    "AUX+PART": 6,
+    "B-ADJ": 7,
+    "B-ADJ+PART": 8,
+    "B-ADP": 9,
+    "B-ADP+ADP": 10,
+    "B-ADV": 11,
+    "B-AUX": 12,
+    "B-AUX+PART": 13,
+    "B-AUX+PART+VERB": 14,
+    "B-CCONJ": 15,
+    "B-DET": 16,
+    "B-INTJ": 17,
+    "B-NOUN": 18,
+    "B-NOUN+PART": 19,
+    "B-NUM": 20,
+    "B-PART": 21,
+    "B-PRON": 22,
+    "B-PRON+AUX": 23,
+    "B-PROPN": 24,
+    "B-PROPN+PART": 25,
+    "B-PUNCT": 26,
+    "B-SCONJ": 27,
+    "B-SYM": 28,
+    "B-VERB": 29,
+    "B-VERB+ADV": 30,
+    "B-VERB+PART": 31,
+    "B-X": 32,
+    "CCONJ": 33,
+    "DET": 34,
+    "I-ADJ": 35,
+    "I-ADJ+PART": 36,
+    "I-ADP": 37,
+    "I-ADP+ADP": 38,
+    "I-ADV": 39,
+    "I-AUX": 40,
+    "I-AUX+PART": 41,
+    "I-AUX+PART+VERB": 42,
+    "I-CCONJ": 43,
+    "I-DET": 44,
+    "I-INTJ": 45,
+    "I-NOUN": 46,
+    "I-NOUN+PART": 47,
+    "I-NUM": 48,
+    "I-PART": 49,
+    "I-PRON": 50,
+    "I-PRON+AUX": 51,
+    "I-PROPN": 52,
+    "I-PROPN+PART": 53,
+    "I-PUNCT": 54,
+    "I-SCONJ": 55,
+    "I-SYM": 56,
+    "I-VERB": 57,
+    "I-VERB+ADV": 58,
+    "I-VERB+PART": 59,
+    "I-X": 60,
+    "INTJ": 61,
+    "NOUN": 62,
+    "NOUN+ADP": 63,
+    "NOUN+PART": 64,
+    "NUM": 65,
+    "PART": 66,
+    "PRON": 67,
+    "PRON+AUX": 68,
+    "PRON+VERB": 69,
+    "PROPN": 70,
+    "PUNCT": 71,
+    "SCONJ": 72,
+    "SYM": 73,
+    "VERB": 74,
+    "VERB+PART": 75,
+    "X": 76
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "task_specific_params": {
+    "upos_multiword": {
+      "ADJ+PART": {
+        "elses": [
+          "else",
+          "s"
+        ],
+        "others": [
+          "other",
+          "s"
+        ]
+      },
+      "ADP+ADP": {
+        "OUTTA": [
+          "OUT",
+          "TA"
+        ]
+      },
+      "ADV+PART": {
+        "into": [
+          "in",
+          "to"
+        ]
+      },
+      "AUX+PART": {
+        "Aren't": [
+          "Are",
+          "n't"
+        ],
+        "CANNOT": [
+          "CAN",
+          "NOT"
+        ],
+        "CANT": [
+          "CA",
+          "NT"
+        ],
+        "Can't": [
+          "Ca",
+          "n't"
+        ],
+        "DON'T": [
+          "DO",
+          "N'T"
+        ],
+        "Don't": [
+          "Do",
+          "n't"
+        ],
+        "Dont": [
+          "Do",
+          "nt"
+        ],
+        "WASN'T": [
+          "WAS",
+          "N'T"
+        ],
+        "ain't": [
+          "ai",
+          "n't"
+        ],
+        "aint": [
+          "ai",
+          "nt"
+        ],
+        "aren't": [
+          "are",
+          "n't"
+        ],
+        "arent": [
+          "are",
+          "nt"
+        ],
+        "can't": [
+          "ca",
+          "n't"
+        ],
+        "cannot": [
+          "can",
+          "not"
+        ],
+        "cant": [
+          "ca",
+          "nt"
+        ],
+        "can\u2019t": [
+          "ca",
+          "n\u2019t"
+        ],
+        "couldn't": [
+          "could",
+          "n't"
+        ],
+        "couldnt": [
+          "could",
+          "nt"
+        ],
+        "didn't": [
+          "did",
+          "n't"
+        ],
+        "didnt": [
+          "did",
+          "nt"
+        ],
+        "didn\u2019t": [
+          "did",
+          "n\u2019t"
+        ],
+        "doesn't": [
+          "does",
+          "n't"
+        ],
+        "doesnt": [
+          "does",
+          "nt"
+        ],
+        "don't": [
+          "do",
+          "n't"
+        ],
+        "dont": [
+          "do",
+          "nt"
+        ],
+        "don\u2019t": [
+          "do",
+          "n\u2019t"
+        ],
+        "haven't": [
+          "have",
+          "n't"
+        ],
+        "havn't": [
+          "hav",
+          "n't"
+        ],
+        "isn't": [
+          "is",
+          "n't"
+        ],
+        "wasent": [
+          "wase",
+          "nt"
+        ],
+        "wasn't": [
+          "was",
+          "n't"
+        ],
+        "won't": [
+          "wo",
+          "n't"
+        ],
+        "wont": [
+          "wo",
+          "nt"
+        ],
+        "won\u2019t": [
+          "wo",
+          "n\u2019t"
+        ],
+        "wouldn't": [
+          "would",
+          "n't"
+        ],
+        "wouldnt": [
+          "would",
+          "nt"
+        ]
+      },
+      "AUX+PART+VERB": {
+        "dunno": [
+          "du",
+          "n",
+          "no"
+        ]
+      },
+      "NOUN+ADP": {
+        "sorta": [
+          "sort",
+          "a"
+        ]
+      },
+      "NOUN+PART": {
+        "DAUGHTERS": [
+          "DAUGHTER",
+          "S"
+        ],
+        "Kids": [
+          "Kid",
+          "s"
+        ],
+        "Smokers": [
+          "Smoker",
+          "s"
+        ],
+        "Travelers": [
+          "Traveler",
+          "s"
+        ],
+        "animals": [
+          "animal",
+          "s"
+        ],
+        "bakers": [
+          "baker",
+          "s"
+        ],
+        "beginners": [
+          "beginner",
+          "s"
+        ],
+        "bettas": [
+          "betta",
+          "s"
+        ],
+        "boys": [
+          "boy",
+          "s"
+        ],
+        "friends": [
+          "friend",
+          "s"
+        ],
+        "grandmas": [
+          "grandma",
+          "s"
+        ],
+        "humans": [
+          "human",
+          "s"
+        ],
+        "manufacturers": [
+          "manufacturer",
+          "s"
+        ],
+        "owners": [
+          "owner",
+          "s"
+        ],
+        "scammers": [
+          "scammer",
+          "s"
+        ],
+        "teams": [
+          "team",
+          "s"
+        ],
+        "visitors": [
+          "visitor",
+          "s"
+        ],
+        "workers": [
+          "worker",
+          "s"
+        ]
+      },
+      "PRON+AUX": {
+        "ITS": [
+          "IT",
+          "S"
+        ],
+        "Im": [
+          "I",
+          "m"
+        ],
+        "Your": [
+          "You",
+          "r"
+        ],
+        "id": [
+          "i",
+          "d"
+        ],
+        "im": [
+          "i",
+          "m"
+        ],
+        "its": [
+          "it",
+          "s"
+        ],
+        "their": [
+          "thei",
+          "r"
+        ],
+        "there": [
+          "the",
+          "re"
+        ],
+        "ur": [
+          "u",
+          "r"
+        ],
+        "your": [
+          "you",
+          "r"
+        ],
+        "youre": [
+          "you",
+          "re"
+        ]
+      },
+      "PRON+VERB": {
+        "im": [
+          "i",
+          "m"
+        ],
+        "its": [
+          "it",
+          "s"
+        ]
+      },
+      "PROPN+PART": {
+        "Friscos": [
+          "Frisco",
+          "s"
+        ],
+        "Mortons": [
+          "Morton",
+          "s"
+        ]
+      },
+      "VERB+ADV": {
+        "c'mon": [
+          "c'm",
+          "on"
+        ]
+      },
+      "VERB+PART": {
+        "Gotta": [
+          "Got",
+          "ta"
+        ],
+        "aren't": [
+          "are",
+          "n't"
+        ],
+        "doesn't": [
+          "does",
+          "n't"
+        ],
+        "doesnt": [
+          "does",
+          "nt"
+        ],
+        "don't": [
+          "do",
+          "n't"
+        ],
+        "gonna": [
+          "gon",
+          "na"
+        ],
+        "gotta": [
+          "got",
+          "ta"
+        ],
+        "isn't": [
+          "is",
+          "n't"
+        ],
+        "wana": [
+          "wan",
+          "a"
+        ],
+        "wasn't": [
+          "was",
+          "n't"
+        ]
+      }
+    }
+  },
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cdbee48cfb38bf2dca5243e3abd1b1b577ca7674cbee2884d750d404b8f001
+size 1110136847

sentencepiece.bpe.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

supar.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2ccc43d9cc310919e3e002f5c8cca9455e35699fe774a85042e916b34484e3
+size 1168116583

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "tokenizer_class": "XLMRobertaTokenizerFast"}