Upload 9 files

models/ud_ewt_gum_pud_20250610/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

models/ud_ewt_gum_pud_20250610/config.json

@@ -0,0 +1,262 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "MultiHeadModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label_maps": {
+    "Abbr": [
+      "X",
+      "Yes"
+    ],
+    "Case": [
+      "X",
+      "Nom",
+      "Acc"
+    ],
+    "Definite": [
+      "X",
+      "Def",
+      "Ind"
+    ],
+    "Degree": [
+      "X",
+      "Sup",
+      "Pos",
+      "Cmp"
+    ],
+    "Foreign": [
+      "X",
+      "Yes"
+    ],
+    "Gender": [
+      "Fem",
+      "X",
+      "Neut",
+      "Masc"
+    ],
+    "Mood": [
+      "X",
+      "Ind",
+      "Imp"
+    ],
+    "NumType": [
+      "Card",
+      "X",
+      "Ord",
+      "Mult"
+    ],
+    "Number": [
+      "X",
+      "Plur",
+      "Sing"
+    ],
+    "Person": [
+      "X",
+      "1",
+      "2",
+      "3"
+    ],
+    "Polarity": [
+      "X",
+      "Neg"
+    ],
+    "Poss": [
+      "X",
+      "Yes"
+    ],
+    "PronType": [
+      "Dem",
+      "Rel",
+      "Prs",
+      "X",
+      "Art",
+      "Int"
+    ],
+    "Reflex": [
+      "X",
+      "Yes"
+    ],
+    "Tense": [
+      "Pres",
+      "X",
+      "Past"
+    ],
+    "VerbForm": [
+      "Ger",
+      "Part",
+      "Fin",
+      "X",
+      "Inf"
+    ],
+    "Voice": [
+      "X",
+      "Pass"
+    ],
+    "deprel": [
+      "cop",
+      "appos",
+      "nmod:tmod",
+      "nmod:poss",
+      "ccomp",
+      "compound",
+      "csubj",
+      "case",
+      "obl:tmod",
+      "cc:preconj",
+      "flat",
+      "compound:prt",
+      "xcomp",
+      "nmod:npmod",
+      "nummod",
+      "aux",
+      "root",
+      "expl",
+      "vocative",
+      "cc",
+      "discourse",
+      "punct",
+      "list",
+      "mark",
+      "nmod",
+      "advmod",
+      "nsubj:pass",
+      "acl:relcl",
+      "acl",
+      "det:predet",
+      "obj",
+      "amod",
+      "advcl",
+      "conj",
+      "aux:pass",
+      "parataxis",
+      "nsubj",
+      "csubj:pass",
+      "det",
+      "iobj",
+      "obl:npmod",
+      "obl",
+      "fixed"
+    ],
+    "pos": [
+      "SYM",
+      "ADV",
+      "NUM",
+      "NOUN",
+      "INTJ",
+      "SCONJ",
+      "PROPN",
+      "ADJ",
+      "PART",
+      "CCONJ",
+      "X",
+      "VERB",
+      "PRON",
+      "PUNCT",
+      "ADP",
+      "AUX",
+      "DET"
+    ],
+    "xpos": [
+      "SYM",
+      "``",
+      "AFX",
+      "ADD",
+      "POS",
+      "PRP$",
+      "NFP",
+      "VBZ",
+      "RBR",
+      "JJ",
+      "JJR",
+      "WRB",
+      "VB",
+      ".",
+      "WP",
+      "RP",
+      "-RRB-",
+      "MD",
+      "PRP",
+      "VBP",
+      "IN",
+      "PDT",
+      "$",
+      "RBS",
+      "FW",
+      "NNS",
+      "-LRB-",
+      ",",
+      "HYPH",
+      "RB",
+      "WP$",
+      "CC",
+      "VBD",
+      "EX",
+      "LS",
+      "CD",
+      "NNP",
+      "NN",
+      "JJS",
+      "VBG",
+      ":",
+      "UH",
+      "''",
+      "DT",
+      "VBN",
+      "WDT",
+      "NNPS",
+      "TO"
+    ]
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_labels_dict": {
+    "Abbr": 2,
+    "Case": 3,
+    "Definite": 3,
+    "Degree": 4,
+    "Foreign": 2,
+    "Gender": 4,
+    "Mood": 3,
+    "NumType": 4,
+    "Number": 3,
+    "Person": 4,
+    "Polarity": 2,
+    "Poss": 2,
+    "PronType": 6,
+    "Reflex": 2,
+    "Tense": 3,
+    "VerbForm": 5,
+    "Voice": 2,
+    "deprel": 43,
+    "pos": 17,
+    "xpos": 48
+  },
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

models/ud_ewt_gum_pud_20250610/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb82ce82b366fcac7a2e4cf25b68a4c5685b3f104a661767c64087d1b6b8de2
+size 783103664

models/ud_ewt_gum_pud_20250610/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/ud_ewt_gum_pud_20250610/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

models/ud_ewt_gum_pud_20250610/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

models/ud_ewt_gum_pud_20250610/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ecbcfdb8463d3a83ca811cbc76f741693919cd4cb81f75e176cc7719038f517
+size 5304