initial release

Browse files

Files changed (7) hide show

README.md +39 -0
config.json +320 -0
pytorch_model.bin +3 -0
special_tokens_map.json +37 -0
supar.model +3 -0
tokenizer_config.json +67 -0
vocab.txt +0 -0

README.md ADDED Viewed

	@@ -0,0 +1,39 @@

+---
+language:
+- "oc"
+tags:
+- "occitan"
+- "token-classification"
+- "pos"
+- "dependency-parsing"
+license: "cc-by-sa-4.0"
+pipeline_tag: "token-classification"
+widget:
+- text: "La mar poiriá encara èsser a la vista."
+---
+# deberta-small-occitan-upos
+## Model Description
+This is a DeBERTa(V2) model pre-trained with [Tolosa Treebank](https://zenodo.org/records/10569962) for POS-tagging and dependency-parsing, derived from [deberta-small-occitan](https://huggingface.co/KoichiYasuoka/deberta-small-occitan). 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/deberta-small-occitan-upos")
+model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/deberta-small-occitan-upos")
+```
+or
+```
+import esupar
+nlp=esupar.load("KoichiYasuoka/deberta-small-occitan-upos")
+```
+## See Also
+[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models

config.json ADDED Viewed

	@@ -0,0 +1,320 @@

+{
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADP+DET",
+    "3": "ADV",
+    "4": "AUX",
+    "5": "B-ADJ",
+    "6": "B-ADP",
+    "7": "B-ADP+DET",
+    "8": "B-ADV",
+    "9": "B-AUX",
+    "10": "B-CCONJ",
+    "11": "B-DET",
+    "12": "B-INTJ",
+    "13": "B-NOUN",
+    "14": "B-NUM",
+    "15": "B-PART",
+    "16": "B-PRON",
+    "17": "B-PROPN",
+    "18": "B-PUNCT",
+    "19": "B-SCONJ",
+    "20": "B-VERB",
+    "21": "B-X",
+    "22": "CCONJ",
+    "23": "DET",
+    "24": "I-ADJ",
+    "25": "I-ADP",
+    "26": "I-ADP+DET",
+    "27": "I-ADV",
+    "28": "I-AUX",
+    "29": "I-CCONJ",
+    "30": "I-DET",
+    "31": "I-INTJ",
+    "32": "I-NOUN",
+    "33": "I-NUM",
+    "34": "I-PART",
+    "35": "I-PRON",
+    "36": "I-PROPN",
+    "37": "I-PUNCT",
+    "38": "I-SCONJ",
+    "39": "I-VERB",
+    "40": "I-X",
+    "41": "INTJ",
+    "42": "NOUN",
+    "43": "NUM",
+    "44": "PART",
+    "45": "PRON",
+    "46": "PROPN",
+    "47": "PUNCT",
+    "48": "SCONJ",
+    "49": "SYM",
+    "50": "VERB",
+    "51": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "label2id": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADP+DET": 2,
+    "ADV": 3,
+    "AUX": 4,
+    "B-ADJ": 5,
+    "B-ADP": 6,
+    "B-ADP+DET": 7,
+    "B-ADV": 8,
+    "B-AUX": 9,
+    "B-CCONJ": 10,
+    "B-DET": 11,
+    "B-INTJ": 12,
+    "B-NOUN": 13,
+    "B-NUM": 14,
+    "B-PART": 15,
+    "B-PRON": 16,
+    "B-PROPN": 17,
+    "B-PUNCT": 18,
+    "B-SCONJ": 19,
+    "B-VERB": 20,
+    "B-X": 21,
+    "CCONJ": 22,
+    "DET": 23,
+    "I-ADJ": 24,
+    "I-ADP": 25,
+    "I-ADP+DET": 26,
+    "I-ADV": 27,
+    "I-AUX": 28,
+    "I-CCONJ": 29,
+    "I-DET": 30,
+    "I-INTJ": 31,
+    "I-NOUN": 32,
+    "I-NUM": 33,
+    "I-PART": 34,
+    "I-PRON": 35,
+    "I-PROPN": 36,
+    "I-PUNCT": 37,
+    "I-SCONJ": 38,
+    "I-VERB": 39,
+    "I-X": 40,
+    "INTJ": 41,
+    "NOUN": 42,
+    "NUM": 43,
+    "PART": 44,
+    "PRON": 45,
+    "PROPN": 46,
+    "PUNCT": 47,
+    "SCONJ": 48,
+    "SYM": 49,
+    "VERB": 50,
+    "X": 51
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 128,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 256,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "task_specific_params": {
+    "upos_multiword": {
+      "ADP+DET": {
+        "Al": [
+          "a",
+          "lo"
+        ],
+        "Au": [
+          "a",
+          "lo"
+        ],
+        "Dau": [
+          "de",
+          "lo"
+        ],
+        "Del": [
+          "de",
+          "lo"
+        ],
+        "Pel": [
+          "per",
+          "lo"
+        ],
+        "Pels": [
+          "per",
+          "los"
+        ],
+        "Peu": [
+          "per",
+          "lo"
+        ],
+        "Sul": [
+          "sus",
+          "lo"
+        ],
+        "Suls": [
+          "sus",
+          "los"
+        ],
+        "ai": [
+          "a",
+          "lei"
+        ],
+        "ais": [
+          "a",
+          "leis"
+        ],
+        "al": [
+          "a",
+          "lo"
+        ],
+        "als": [
+          "a",
+          "los"
+        ],
+        "ara": [
+          "a",
+          "era"
+        ],
+        "ath": [
+          "a",
+          "eth"
+        ],
+        "au": [
+          "a",
+          "lo"
+        ],
+        "aus": [
+          "a",
+          "los"
+        ],
+        "dau": [
+          "de",
+          "lo"
+        ],
+        "daus": [
+          "de",
+          "los"
+        ],
+        "dei": [
+          "de",
+          "lei"
+        ],
+        "del": [
+          "de",
+          "lo"
+        ],
+        "dels": [
+          "de",
+          "los"
+        ],
+        "dera": [
+          "de",
+          "era"
+        ],
+        "deras": [
+          "de",
+          "eras"
+        ],
+        "des": [
+          "de",
+          "es"
+        ],
+        "deth": [
+          "de",
+          "eth"
+        ],
+        "deu": [
+          "de",
+          "lo"
+        ],
+        "deus": [
+          "de",
+          "los"
+        ],
+        "entau": [
+          "ent\u00e0",
+          "lo"
+        ],
+        "entaus": [
+          "ent\u00e0",
+          "los"
+        ],
+        "jol": [
+          "jos",
+          "lo"
+        ],
+        "jols": [
+          "jos",
+          "los"
+        ],
+        "pel": [
+          "per",
+          "lo"
+        ],
+        "pels": [
+          "per",
+          "los"
+        ],
+        "pera": [
+          "per",
+          "era"
+        ],
+        "peth": [
+          "per",
+          "eth"
+        ],
+        "peu": [
+          "per",
+          "lo"
+        ],
+        "peus": [
+          "per",
+          "los"
+        ],
+        "sul": [
+          "sus",
+          "lo"
+        ],
+        "suls": [
+          "sus",
+          "los"
+        ],
+        "suu": [
+          "sus",
+          "lo"
+        ],
+        "tath": [
+          "ta",
+          "eth"
+        ],
+        "tau": [
+          "ta",
+          "lo"
+        ]
+      }
+    }
+  },
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 0,
+  "vocab_size": 30000
+}

pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:daa0cfbb2240f96bd8366c0c16346822b532021b4ddb8e686afafc3fcfab908f
+size 69044258

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

supar.model ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:65166e5dd3d9fadc18b907e2b9385fd216b2d751da405f544efc87b8db337c58
+size 115178818

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,67 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 126,
+  "model_max_length": 128,
+  "never_split": [
+    "[CLS]",
+    "[PAD]",
+    "[SEP]",
+    "[UNK]",
+    "[MASK]"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

vocab.txt ADDED Viewed

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