initial release

README.md

@@ -0,0 +1,44 @@
+---
+language:
+- "vi"
+tags:
+- "vietnamese"
+- "token-classification"
+- "pos"
+- "dependency-parsing"
+datasets:
+- "universal_dependencies"
+license: "cc-by-sa-4.0"
+pipeline_tag: "token-classification"
+widget:
+- text: "Hai cái đầu thì tốt hơn một."
+---
+
+# bert-base-vietnamese-upos
+
+## Model Description
+
+This is a BERT model pre-trained on Vietnamese texts for POS-tagging and dependency-parsing, derived from [vibert-base-cased](https://huggingface.co/FPTAI/vibert-base-cased). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/)(Universal Part-Of-Speech).
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModelForTokenClassification,TokenClassificationPipeline
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/bert-base-vietnamese-upos")
+model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/bert-base-vietnamese-upos")
+pipeline=TokenClassificationPipeline(tokenizer=tokenizer,model=model,aggregation_strategy="simple")
+nlp=lambda x:[(x[t["start"]:t["end"]],t["entity_group"]) for t in pipeline(x)]
+print(nlp("Hai cái đầu thì tốt hơn một."))
+```
+
+or
+
+```py
+import esupar
+nlp=esupar.load("KoichiYasuoka/bert-base-vietnamese-upos")
+print(nlp("Hai cái đầu thì tốt hơn một."))
+```
+
+## See Also
+
+[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models

config.json

@@ -0,0 +1,134 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADV",
+    "3": "AUX",
+    "4": "B-ADJ",
+    "5": "B-ADP",
+    "6": "B-ADV",
+    "7": "B-AUX",
+    "8": "B-DET",
+    "9": "B-INTJ",
+    "10": "B-NOUN",
+    "11": "B-NUM",
+    "12": "B-PART",
+    "13": "B-PRON",
+    "14": "B-PROPN",
+    "15": "B-PUNCT",
+    "16": "B-SCONJ",
+    "17": "B-SYM",
+    "18": "B-VERB",
+    "19": "B-X",
+    "20": "CCONJ",
+    "21": "DET",
+    "22": "I-ADJ",
+    "23": "I-ADP",
+    "24": "I-ADV",
+    "25": "I-AUX",
+    "26": "I-DET",
+    "27": "I-INTJ",
+    "28": "I-NOUN",
+    "29": "I-NUM",
+    "30": "I-PART",
+    "31": "I-PRON",
+    "32": "I-PROPN",
+    "33": "I-PUNCT",
+    "34": "I-SCONJ",
+    "35": "I-SYM",
+    "36": "I-VERB",
+    "37": "I-X",
+    "38": "INTJ",
+    "39": "NOUN",
+    "40": "NUM",
+    "41": "PART",
+    "42": "PRON",
+    "43": "PROPN",
+    "44": "PUNCT",
+    "45": "SCONJ",
+    "46": "SYM",
+    "47": "VERB",
+    "48": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADV": 2,
+    "AUX": 3,
+    "B-ADJ": 4,
+    "B-ADP": 5,
+    "B-ADV": 6,
+    "B-AUX": 7,
+    "B-DET": 8,
+    "B-INTJ": 9,
+    "B-NOUN": 10,
+    "B-NUM": 11,
+    "B-PART": 12,
+    "B-PRON": 13,
+    "B-PROPN": 14,
+    "B-PUNCT": 15,
+    "B-SCONJ": 16,
+    "B-SYM": 17,
+    "B-VERB": 18,
+    "B-X": 19,
+    "CCONJ": 20,
+    "DET": 21,
+    "I-ADJ": 22,
+    "I-ADP": 23,
+    "I-ADV": 24,
+    "I-AUX": 25,
+    "I-DET": 26,
+    "I-INTJ": 27,
+    "I-NOUN": 28,
+    "I-NUM": 29,
+    "I-PART": 30,
+    "I-PRON": 31,
+    "I-PROPN": 32,
+    "I-PUNCT": 33,
+    "I-SCONJ": 34,
+    "I-SYM": 35,
+    "I-VERB": 36,
+    "I-X": 37,
+    "INTJ": 38,
+    "NOUN": 39,
+    "NUM": 40,
+    "PART": 41,
+    "PRON": 42,
+    "PROPN": 43,
+    "PUNCT": 44,
+    "SCONJ": 45,
+    "SYM": 46,
+    "VERB": 47,
+    "X": 48
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 38168
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39af228b8bf4fc9cc073b1c799bea7251ebb29fa791d0b6e2c1c748fb404511
+size 459276273

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

supar.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e540952e65c6a3a6f19084f41a5a5423aa0df4bc2bce5af69e795f4f580d05
+size 509894565

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizerFast",
+  "unk_token": "[UNK]"
+}